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

    Neuronpedia

    INDEX
    Explanations

    symbols or expressions denoting mathematical relationships or conditions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    y
    -0.79
     &
    -0.66
    lgari
    -0.66
     W
    -0.65
     <
    -0.64
     Peterson
    -0.64
     Champ
    -0.64
     Willoughby
    -0.64
     Gentry
    -0.64
    ud
    -0.63
    POSITIVE LOGITS
     themſelves
    1.20
     myſelf
    1.19
     Diſ
    1.16
     Theſe
    1.14
    &\
    1.12
     himſelf
    1.12
     itſelf
    1.11
     ſeveral
    1.07
     &\
    1.06
     Anſ
    1.05
    Act Density 0.006%

    No Known Activations