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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically commas and periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    amate
    -0.17
    ividual
    -0.16
    425
    -0.15
    lace
    -0.15
    .createClass
    -0.14
    sembl
    -0.14
    aybe
    -0.14
    andır
    -0.14
    hap
    -0.14
    oton
    -0.13
    POSITIVE LOGITS
     Ore
    0.18
    wi
    0.15
    ych
    0.14
     Pazar
    0.14
    aidu
    0.14
    имÑĥ
    0.14
    BuilderFactory
    0.14
    ainer
    0.14
    331
    0.14
    _GC
    0.14
    Act Density 0.012%

    No Known Activations