INDEX
Explanations
reflexive pronouns
This neuron activates on occurrences of “found” paired with a reflexive pronoun (e.g. “found themselves” or “found herself”) indicating a moment of self-realization.
New Auto-Interp
Negative Logits
cerr
-0.07
Yard
-0.07
sopr
-0.06
STATIC
-0.06
agents
-0.06
gson
-0.06
Essen
-0.06
Close
-0.06
espect
-0.06
_DEC
-0.06
POSITIVE LOGITS
рами
0.06
새
0.06
итом
0.06
설명
0.06
θε
0.06
854
0.06
AIT
0.06
Schiff
0.06
åde
0.06
나를
0.06
Activations Density 0.009%