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

    Neuronpedia

    INDEX
    Explanations

    terms related to perception and assessment indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     saveiro
    -0.73
     ModelExpression
    -0.72
     vulgaires
    -0.71
    SPATH
    -0.70
     duplo
    -0.69
    RenderAtEndOf
    -0.68
     Gaut
    -0.68
     Câmara
    -0.67
     Sancho
    -0.65
     cardia
    -0.65
    POSITIVE LOGITS
     a
    0.86
     being
    0.81
     “
    0.76
     an
    0.73
     be
    0.71
     "
    0.68
    writerow
    0.66
     truly
    0.66
     ‘
    0.65
    PreferredItem
    0.64
    Act Density 0.305%

    No Known Activations