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

    Neuronpedia

    INDEX
    Explanations

    phrases and proper nouns related to science fiction and technology

    oai_token-act-pair · gpt-3.5-turbo

    references to personal identity and emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Solitaire
    -0.57
     of
    -0.55
     Of
    -0.54
     graphene
    -0.52
     OF
    -0.52
     Arpaio
    -0.49
     Mechdragon
    -0.49
     Socialism
    -0.49
     Malfoy
    -0.47
     JUSTICE
    -0.47
    POSITIVE LOGITS
    nesday
    0.69
    DeliveryDate
    0.66
    anwhile
    0.65
     exting
    0.64
    ÃĥÃĤ
    0.64
     teasp
    0.64
    StreamerBot
    0.63
    foreseen
    0.61
    fold
    0.60
    eger
    0.59
    Act Density 1.175%

    No Known Activations