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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or contemplation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    حياته
    -0.64
    例文帳に追加
    -0.63
    mobileqq
    -0.60
    śmy
    -0.57
     ALG
    -0.56
    __':
    -0.56
    asyarakat
    -0.56
    ={`/
    -0.54
    UnknownFields
    -0.54
    breit
    -0.54
    POSITIVE LOGITS
    Hmm
    0.88
    Huh
    0.81
    Ahh
    0.79
    Hmmmm
    0.78
    Hmmm
    0.77
    Mmm
    0.77
    ah
    0.76
     Ah
    0.76
     Hmm
    0.75
    Mmmm
    0.72
    Act Density 0.152%

    No Known Activations