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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically periods and commas

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     exploration
    -0.54
    DoubleQuotes
    -0.48
    aud
    -0.46
     gron
    -0.46
     nhàng
    -0.45
    Psy
    -0.44
     flags
    -0.44
     dispu
    -0.41
     revisited
    -0.41
    bal
    -0.41
    POSITIVE LOGITS
    enumii
    0.67
     createSlice
    0.66
     >=",
    0.65
    Personensuche
    0.63
    EDEFAULT
    0.63
     المعيارى
    0.61
    ########.
    0.61
     délib
    0.60
    antMatchers
    0.60
    hoeddwyd
    0.60
    Act Density 0.009%

    No Known Activations