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

    Neuronpedia

    INDEX
    Explanations

    mixed alphanumeric characters with accents

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.72
     Perkins
    -0.71
    WARD
    -0.68
    mort
    -0.68
     Mandela
    -0.68
     Binary
    -0.67
    izable
    -0.66
     Dragonbound
    -0.63
    ifying
    -0.63
    ilater
    -0.63
    POSITIVE LOGITS
    ĥ
    1.77
    Ģ
    1.47
    Ĵ
    1.46
    ī
    1.46
    Į
    1.46
    ı
    1.43
    Ĺ
    1.43
    ķ
    1.43
    Ń
    1.40
    İ
    1.39
    Act Density 0.016%

    No Known Activations