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

    Neuronpedia

    INDEX
    Explanations

    cultural references and mentions

    oai_token-act-pair · gpt-3.5-turbo

    references to various cultures and their interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ZE
    -0.69
     Nost
    -0.67
    Operation
    -0.63
    Naz
    -0.61
    Boy
    -0.61
     stewards
    -0.60
    ãĥª
    -0.60
     Relief
    -0.59
    ר
    -0.58
     visitation
    -0.58
    POSITIVE LOGITS
    paces
    1.30
    mith
    1.18
    hops
    1.17
    hips
    1.17
    cale
    1.15
    chool
    1.11
    poons
    1.10
    cape
    1.06
    ettings
    1.03
    pace
    1.03
    Act Density 0.171%

    No Known Activations