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

    Neuronpedia

    INDEX
    Explanations

    numeric values and their associated punctuation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    setVerticalGroup
    -0.95
     itſelf
    -0.95
     ProtoMessage
    -0.86
    PreferredItem
    -0.84
     Lightboxes
    -0.82
    enterOuterAlt
    -0.82
     BoxFit
    -0.81
    onavir
    -0.79
    AndEndTag
    -0.78
     Réponses
    -0.77
    POSITIVE LOGITS
     et
    0.39
     than
    0.39
    jsdelivr
    0.39
    [toxicity=0]
    0.36
     attempts
    0.36
    </blockquote>
    0.35
    days
    0.35
     ilk
    0.34
    .
    0.34
    </h3>
    0.34
    Act Density 0.008%

    No Known Activations