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

    Neuronpedia

    INDEX
    Explanations

    parentheses and comma usage in code or technical documentation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    legg
    -0.59
    けどね
    -0.57
    ices
    -0.56
     party
    -0.56
    tawa
    -0.56
     subject
    -0.56
     bienvenue
    -0.54
     σχέ
    -0.54
    TOE
    -0.54
    еве
    -0.53
    POSITIVE LOGITS
     outcrops
    0.59
     nahilalakip
    0.57
     sī
    0.57
    copg
    0.57
     puffs
    0.56
    ISupport
    0.55
     Brethren
    0.55
    potranspiration
    0.55
    ReusableCell
    0.54
     Вікіпе
    0.54
    Act Density 0.001%

    No Known Activations