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

    Neuronpedia

    INDEX
    Explanations

    references to original works and adaptations in various forms of media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rum
    -0.14
    alo
    -0.14
    olk
    -0.14
    trand
    -0.14
    ัà¸ĩà¸Ļ
    -0.13
    anged
    -0.13
    lien
    -0.13
     trái
    -0.13
    thinkable
    -0.12
     upcoming
    -0.12
    POSITIVE LOGITS
     original
    1.30
    original
    1.09
     originals
    1.05
     Original
    0.98
     ORIGINAL
    0.95
     originally
    0.93
    -original
    0.93
    Original
    0.91
    (original
    0.86
    _original
    0.85
    Act Density 0.506%

    No Known Activations