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

    Neuronpedia

    INDEX
    Explanations

    references to inclusion and removal in lists or collections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     điệu
    -0.69
    úrate
    -0.66
     déchir
    -0.59
    telling
    -0.57
    assioned
    -0.57
     Schro
    -0.55
    zige
    -0.54
    TELL
    -0.54
     appuy
    -0.54
    謳
    -0.52
    POSITIVE LOGITS
     ModelExpression
    0.92
    ⓧ
    0.86
    BufferException
    0.82
    Rüyada
    0.77
    kuuta
    0.76
     буенча
    0.74
     بيها
    0.74
     tarihinde
    0.74
    ⓘ
    0.73
     насељу
    0.72
    Act Density 0.121%

    No Known Activations