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

    Neuronpedia

    INDEX
    Explanations

    terms associated with statistical significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.86
    حياته
    -0.78
     EconPapers
    -0.77
     plainte
    -0.73
     Picchu
    -0.72
    RenderAtEndOf
    -0.72
    try
    -0.72
     HasFactory
    -0.71
    oa̍t
    -0.71
     חיצוניים
    -0.70
    POSITIVE LOGITS
     considered
    2.46
     Considered
    2.18
    considered
    2.10
     deemed
    1.73
     regarded
    1.69
     considerado
    1.67
     considerada
    1.56
     considerados
    1.53
     consideradas
    1.46
     considerato
    1.40
    Act Density 0.090%

    No Known Activations