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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly commas and periods

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     riuscito
    -0.73
     elettrico
    -0.67
     Iced
    -0.65
     Electra
    -0.63
    Bronnen
    -0.61
     šaty
    -0.61
     Farid
    -0.61
     Majefty
    -0.61
     roulant
    -0.61
     enlever
    -0.60
    POSITIVE LOGITS
    \,.
    0.98
    \,,
    0.88
    tanleria
    0.72
    getClassLoader
    0.70
     nahilalakip
    0.68
     BoxFit
    0.67
    abestanden
    0.66
    cetes
    0.66
    HasForeignKey
    0.66
     متحده
    0.66
    Act Density 0.012%

    No Known Activations