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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making

    oai_token-act-pair · gpt-3.5-turbo

    phrases that present alternatives or options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tes
    -0.60
    escription
    -0.56
    HEAD
    -0.56
    STE
    -0.54
     Tec
    -0.53
     tremend
    -0.53
    Þ
    -0.53
     rall
    -0.52
     pione
    -0.51
     Scrib
    -0.51
    POSITIVE LOGITS
    not
    0.90
     not
    0.89
     NOT
    0.78
    nam
    0.68
    Not
    0.67
     Marketable
    0.65
     Not
    0.62
    å¦
    0.62
    ados
    0.61
     how
    0.61
    Act Density 0.013%

    No Known Activations