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

    Neuronpedia

    INDEX
    Explanations

    symbols and punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     but
    -0.59
     careful
    -0.58
    WriteLiteral
    -0.57
     se
    -0.55
     ke
    -0.54
    Cordialement
    -0.53
     an
    -0.52
    commut
    -0.51
     so
    -0.50
     lo
    -0.50
    POSITIVE LOGITS
     للمعارف
    0.93
     ExecuteAsync
    0.92
     myſelf
    0.91
    intios
    0.86
     raiſ
    0.85
     inſ
    0.83
    ſelf
    0.82
     مرئيه
    0.82
     itſelf
    0.82
     unſ
    0.82
    Act Density 0.045%

    No Known Activations