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

    Neuronpedia

    INDEX
    Explanations

    elements related to classifications or categories, particularly in a hierarchical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -0.71
     zprávy
    -0.50
     develops
    -0.50
     аренду
    -0.49
    ,
    -0.48
     européennes
    -0.48
     jeter
    -0.48
    _
    -0.48
     combine
    -0.48
    .
    -0.47
    POSITIVE LOGITS
    клопе
    0.95
    chila
    0.79
    ometal
    0.76
    meneu
    0.75
    umesc
    0.73
    moiselle
    0.73
    EndContext
    0.72
    AutoresizingMask
    0.72
    dymyr
    0.70
    NUMX
    0.70
    Act Density 1.410%

    No Known Activations