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

    Neuronpedia

    INDEX
    Explanations

    words indicating precision and exactness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Infór
    -0.67
     enfans
    -0.66
     ennemi
    -0.65
    WriteBarrier
    -0.61
     alugar
    -0.60
     HasFactory
    -0.60
     zijne
    -0.60
     consommate
    -0.60
     chrétien
    -0.59
     mijne
    -0.59
    POSITIVE LOGITS
     precise
    0.73
     precisely
    0.72
     twist
    0.66
     Precise
    0.66
    Precise
    0.62
     clean
    0.62
    import
    0.60
     exactly
    0.59
    precise
    0.58
     pattern
    0.56
    Act Density 0.191%

    No Known Activations