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

    Neuronpedia

    INDEX
    Explanations

    mentions of change or variation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "change."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    APH
    -0.76
    amina
    -0.76
    ç«
    -0.73
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.72
    -+-+
    -0.71
    onz
    -0.70
     SPR
    -0.70
    sonian
    -0.69
     LIMITED
    -0.66
     QR
    -0.66
    POSITIVE LOGITS
    ogue
    0.82
    overs
    0.81
    ĸļ
    0.77
    agents
    0.77
    xual
    0.74
    over
    0.72
    imedia
    0.71
    ulkan
    0.70
    atile
    0.70
     blindness
    0.69
    Act Density 0.028%

    No Known Activations