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

    Neuronpedia

    INDEX
    Explanations

    text that indicates high numerical or statistical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     “
    -0.72
     new
    -0.64
     "
    -0.62
     big
    -0.62
    <eos>
    -0.62
     that
    -0.60
     If
    -0.58
     current
    -0.58
     the
    -0.57
     it
    -0.56
    POSITIVE LOGITS
    SourceChecksum
    0.80
     disambiguazione
    0.79
     صوتيه
    0.75
    featureID
    0.74
    InjectAttribute
    0.73
     enfans
    0.73
    EDEFAULT
    0.71
     AppColors
    0.71
    PullParser
    0.70
    سطس
    0.69
    Act Density 0.178%

    No Known Activations