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

    Neuronpedia

    INDEX
    Explanations

    percentage values in text

    oai_token-act-pair · gpt-3.5-turbo

    quantitative data and percentages related to sales or trade statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     convol
    -0.57
    verbs
    -0.53
    urdy
    -0.52
    byter
    -0.51
    Aid
    -0.51
    hess
    -0.50
     groom
    -0.49
     Bold
    -0.49
     Tune
    -0.49
    lished
    -0.48
    POSITIVE LOGITS
     of
    1.21
    of
    1.08
     thereof
    0.94
    OF
    0.93
    Of
    0.87
     Of
    0.79
     OF
    0.78
     fewer
    0.71
    PsyNetMessage
    0.69
    ãĥ»
    0.67
    Act Density 0.090%

    No Known Activations