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

    Neuronpedia

    INDEX
    Explanations

    similes that compare two dissimilar things using "like" or "as."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DataAnnotations
    -0.62
    Apparently
    -0.60
     apparently
    -0.60
     mainly
    -0.59
    Mainly
    -0.59
     Apparently
    -0.59
    mainly
    -0.57
     Mainly
    -0.56
    apparently
    -0.54
     aparentemente
    -0.52
    POSITIVE LOGITS
    NUMX
    0.66
    édrale
    0.59
    υμ
    0.58
     olisi
    0.58
    epam
    0.58
     fieldNum
    0.57
    hilation
    0.57
    醐
    0.57
    styleType
    0.57
     الرياضيه
    0.56
    Act Density 0.192%

    No Known Activations