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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or indecision

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    endregion
    -0.63
     Majefty
    -0.61
     BJ
    -0.58
     Litu
    -0.57
    tonsoft
    -0.56
    UAWEI
    -0.55
     ár
    -0.54
     =
    -0.53
    $',
    -0.53
    BJ
    -0.52
    POSITIVE LOGITS
    Dunno
    0.82
     unknow
    0.79
    دانشنامهٔ
    0.74
     dunno
    0.71
    知らない
    0.68
     дописавши
    0.67
    know
    0.66
     vetorial
    0.66
    也不知道
    0.65
     desconoc
    0.64
    Act Density 0.110%

    No Known Activations