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

    Neuronpedia

    INDEX
    Explanations

    quotations

    oai_token-act-pair · gpt-3.5-turbo

    quotations or dialogue within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     evid
    -0.76
     allied
    -0.73
     adjud
    -0.73
     revers
    -0.73
     litter
    -0.72
     arch
    -0.72
     disputed
    -0.72
     repro
    -0.71
     regulated
    -0.71
     displaced
    -0.71
    POSITIVE LOGITS
    Yeah
    1.72
    Honestly
    1.72
    Everybody
    1.71
    I
    1.68
    Absolutely
    1.64
    It
    1.64
    Obviously
    1.63
    Everything
    1.63
    We
    1.62
    My
    1.60
    Act Density 0.109%

    No Known Activations