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

    Neuronpedia

    INDEX
    Explanations

    percentages and numbers with decimal points

    oai_token-act-pair · gpt-3.5-turbo

    numerical data or statistical information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     prosec
    -0.92
     sculpt
    -0.86
     reneg
    -0.82
     silenced
    -0.82
     sil
    -0.82
     agon
    -0.79
     holog
    -0.77
     incarn
    -0.75
     cult
    -0.75
     rubber
    -0.73
    POSITIVE LOGITS
    Overall
    1.73
    Among
    1.71
    Percent
    1.69
    Average
    1.69
    Compared
    1.63
    Of
    1.52
    Across
    1.52
    Between
    1.50
    Looking
    1.49
    Interestingly
    1.47
    Act Density 0.322%

    No Known Activations