Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and symbols

    oai_token-act-pair · gpt-3.5-turbo

    patterns and elements related to structured data presentations, possibly mathematical or graphical layouts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĢ¦"
    -0.75
    "—
    -0.74
    —"
    -0.68
    anski
    -0.64
     incorpor
    -0.63
     exerc
    -0.63
     depl
    -0.63
     advoc
    -0.61
    aiman
    -0.61
     stret
    -0.60
    POSITIVE LOGITS
     |
    2.78
    |
    2.18
     ||
    1.82
     }}
    1.60
    )|
    1.59
    ||
    1.51
    -|
    1.50
     [|
    1.45
     |--
    1.42
     +---
    1.37
    Act Density 0.070%

    No Known Activations