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

    Neuronpedia

    INDEX
    Explanations

    mathematical or formal expressions related to proofs and mathematical properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pun
    -0.41
     slip
    -0.41
    ัล
    -0.41
    những
    -0.41
     studios
    -0.40
     ek
    -0.40
    一
    -0.40
    いっぱい
    -0.40
    義
    -0.40
    slip
    -0.39
    POSITIVE LOGITS
    :✨
    0.87
    hoeddwyd
    0.85
    Personendaten
    0.84
    Tikang
    0.83
    HideFlags
    0.79
    findpost
    0.75
    тьяна
    0.73
     незавершена
    0.72
    0.71
     AppModule
    0.70
    Act Density 1.987%

    No Known Activations