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

    Neuronpedia

    INDEX
    Explanations

    sentences expressing personal opinions or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     supposedly
    -0.58
     reportedly
    -0.55
     allegedly
    -0.55
     supuestamente
    -0.55
     nomme
    -0.48
     alleged
    -0.47
     toegang
    -0.47
     siger
    -0.46
     Puli
    -0.46
     purported
    -0.45
    POSITIVE LOGITS
     insuffisamment
    0.93
     فريبيس
    0.85
    enumii
    0.84
     *)__
    0.83
     ExecuteAsync
    0.83
    клопе
    0.82
     للمعارف
    0.82
    enumi
    0.81
    :✨
    0.78
     تانيه
    0.78
    Act Density 0.266%

    No Known Activations