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

    Neuronpedia

    INDEX
    Explanations

    phrases that express limitations or impossibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ⓧ
    -1.02
    ніципалі
    -0.61
     Infór
    -0.59
     الرياضيه
    -0.59
    $_['
    -0.59
     فريبيس
    -0.58
    harapkan
    -0.58
    berdayakan
    -0.57
     antidesliz
    -0.57
    -0.56
    POSITIVE LOGITS
     other
    0.53
     never
    0.39
     unimaginable
    0.39
     nt
    0.36
     NT
    0.36
     Mac
    0.35
    其他人
    0.34
     Sab
    0.33
     Impossible
    0.33
    其他
    0.33
    Act Density 0.342%

    No Known Activations