INDEX

Explanations

TR followed by P or N

np_acts-logits-general · gemini-2.5-flash-lite

The neuron is a detector for the character sequence “tr” (in any casing) within tokens.

oai_token-act-pair · o4-mini Triggered by @jyhe0408

the character sequence “tr” (often capitalized “TR”) at the start of words and acronyms.

oai_token-act-pair · gpt-5 Triggered by @jyhe0408

the abbreviation "TRP" (transient receptor potential) in scientific and technical contexts.

oai_token-act-pair · claude-4-5-sonnet Triggered by @jyhe0408

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_34/width_131k

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 же

-0.87

と

-0.84

 however

-0.84

では

-0.83

-0.79

も

-0.79

와

-0.79

ה

-0.78

这个

-0.77

 Revi

-0.75

POSITIVE LOGITS

TR

1.34

Tr

1.22

트

1.05

Tr

1.02

TRL

1.01

TR

0.99

TRC

0.99

trx

0.93

 ट्र

0.90

ditional

0.88

Activations Density 0.020%

TR followed by P or N

The neuron is a detector for the character sequence “tr” (in any casing) within tokens.

the character sequence “tr” (often capitalized “TR”) at the start of words and acronyms.

the abbreviation "TRP" (transient receptor potential) in scientific and technical contexts.

No Comments

No Known Activations

TR followed by P or N

The neuron is a detector for the character sequence “tr” (in any casing) within tokens.

the character sequence “tr” (often capitalized “TR”) at the start of words and acronyms.

the abbreviation "TRP" (transient receptor potential) in scientific and technical contexts.

No Comments

No Known Activations