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

    Neuronpedia

    INDEX
    Explanations

    references to additional or alternative examples or choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.97
     ſtate
    -0.85
     سكانية
    -0.81
     leaſt
    -0.78
     Majefty
    -0.78
     Efq
    -0.78
    Rohy
    -0.78
     Anſ
    -0.77
     myſelf
    -0.77
     purpoſe
    -0.76
    POSITIVE LOGITS
     Other
    0.78
    Other
    0.74
     Others
    0.71
    Others
    0.69
     other
    0.66
    OTHER
    0.59
    Otras
    0.59
    autres
    0.57
    此外
    0.56
     còn
    0.54
    Act Density 0.159%

    No Known Activations