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

    Neuronpedia

    INDEX
    Explanations

    references to people and their roles or positions in society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     small
    -0.36
     wire
    -0.35
     intervene
    -0.32
     ved
    -0.31
     dép
    -0.31
     carro
    -0.31
    TypedDataSet
    -0.31
     Su
    -0.31
    gra
    -0.30
     Grund
    -0.30
    POSITIVE LOGITS
     surla
    0.62
    parsedMessage
    0.61
    UnusedPrivate
    0.58
    RenderAtEndOf
    0.55
     GenerationType
    0.55
    <?
    0.54
    enderror
    0.53
    ⓧ
    0.52
    0.52
     endfor
    0.52
    Act Density 0.909%

    No Known Activations