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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    empty string sequences or segments that indicate the absence of content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     conclud
    -0.81
     tremend
    -0.78
     [*
    -0.76
     destro
    -0.75
    ãĥ¼ãĥĨ
    -0.75
     thous
    -0.71
     proport
    -0.70
     behavi
    -0.69
     proble
    -0.68
     ingred
    -0.67
    POSITIVE LOGITS
    utenant
    0.76
    letters
    0.71
    oba
    0.70
    tall
    0.65
    adh
    0.65
    coin
    0.64
    gallery
    0.64
    tt
    0.63
    av
    0.62
    anie
    0.62
    Act Density 0.078%

    No Known Activations