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

    Neuronpedia

    INDEX
    Explanations

    mentions of individuals and their personal experiences or positions in a community context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ñıк
    -0.15
    ificent
    -0.14
    egend
    -0.14
    antha
    -0.14
     prés
    -0.14
    assage
    -0.14
    ossa
    -0.13
    ibling
    -0.13
    ArgumentException
    -0.13
    ادا
    -0.13
    POSITIVE LOGITS
     credits
    0.26
    credits
    0.22
     credit
    0.21
     Credits
    0.20
     said
    0.20
     says
    0.19
     admit
    0.18
    Credit
    0.18
     admits
    0.17
     admitting
    0.17
    Act Density 0.137%

    No Known Activations