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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roadcast
    -0.17
    iei
    -0.16
    roids
    -0.15
    ityEngine
    -0.15
    NotificationCenter
    -0.14
    peaker
    -0.14
    ensa
    -0.14
    اء
    -0.14
    /XMLSchema
    -0.14
    jÃŃ
    -0.14
    POSITIVE LOGITS
    ipe
    0.17
    pon
    0.15
    yt
    0.15
     Intr
    0.14
    upo
    0.14
     Folk
    0.14
     upon
    0.14
     Super
    0.14
    yp
    0.14
    iju
    0.14
    Act Density 0.247%

    No Known Activations