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

    Neuronpedia

    INDEX
    Explanations

    expressions of hesitation or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alse
    -0.18
     ëĭ¤ìļ´ë°Ľê¸°
    -0.14
     Integral
    -0.14
    aft
    -0.14
    INTR
    -0.14
    اخ
    -0.14
    енÑģ
    -0.14
    erule
    -0.14
    paces
    -0.13
    طة
    -0.13
    POSITIVE LOGITS
    braco
    0.29
    bral
    0.28
    gebung
    0.27
    fang
    0.25
    pte
    0.25
    rah
    0.23
    rella
    0.23
    kehr
    0.22
    ami
    0.21
    arked
    0.20
    Act Density 0.009%

    No Known Activations