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

    Neuronpedia

    INDEX
    Explanations

    instances of specific actions or events related to death or killing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gross
    -0.07
    uzey
    -0.07
    robat
    -0.07
    uate
    -0.06
     sl
    -0.06
    शन
    -0.06
    culate
    -0.06
    ivan
    -0.06
    swick
    -0.06
    embre
    -0.06
    POSITIVE LOGITS
    unn
    0.07
    unit
    0.07
    dy
    0.07
    .mapbox
    0.06
    Nullable
    0.06
    igsaw
    0.06
     done
    0.06
    аÑĤок
    0.06
    -done
    0.06
    ubits
    0.06
    Act Density 0.001%

    No Known Activations