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

    Neuronpedia

    INDEX
    Explanations

    technical terms and abbreviations

    oai_token-act-pair · gpt-3.5-turbo

    phrases or clauses that indicate an alternative or choice within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ires
    -0.91
    rodu
    -0.87
    ights
    -0.73
    vertising
    -0.71
    IDENT
    -0.71
    eways
    -0.70
    erest
    -0.68
    natureconservancy
    -0.67
    onday
    -0.67
    IGHTS
    -0.67
    POSITIVE LOGITS
    acle
    1.15
    chard
    1.13
    acles
    1.02
    chid
    0.97
    nam
    0.96
     alternatively
    0.96
    ifice
    0.94
    chest
    0.90
    Else
    0.89
    ific
    0.88
    Act Density 0.077%

    No Known Activations