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

    Neuronpedia

    INDEX
    Explanations

    content related to guidelines and restrictions on acceptable behavior or language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ear
    -0.17
    acier
    -0.16
    arsing
    -0.15
    SOR
    -0.14
    ifo
    -0.14
    otec
    -0.14
    earned
    -0.14
     Sie
    -0.14
    achable
    -0.14
    eyh
    -0.13
    POSITIVE LOGITS
    дам
    0.16
    aat
    0.15
     nor
    0.15
    訴
    0.15
     nÃło
    0.15
    _below
    0.14
    ym
    0.14
     unless
    0.14
    _DISPATCH
    0.14
     PRI
    0.14
    Act Density 0.166%

    No Known Activations