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

    Neuronpedia

    INDEX
    Explanations

    references to cinema and films

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ertoire
    -0.16
    orgot
    -0.15
    Äĥ
    -0.15
    ACHE
    -0.14
    аÑĤкÑĥ
    -0.14
    holding
    -0.14
    dens
    -0.14
    naments
    -0.14
    atum
    -0.14
    a
    -0.14
    POSITIVE LOGITS
    ży
    0.17
    oodoo
    0.15
    Falsy
    0.14
    館
    0.14
    ilik
    0.14
    stial
    0.14
    emens
    0.14
    astes
    0.13
    alse
    0.13
    -wide
    0.13
    Act Density 0.009%

    No Known Activations