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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically parentheses and commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assi
    -0.15
    arian
    -0.15
    enegro
    -0.15
    azu
    -0.15
    865
    -0.15
    azzi
    -0.15
    arians
    -0.15
    attle
    -0.15
     Lam
    -0.14
    ourd
    -0.14
    POSITIVE LOGITS
    ruz
    0.16
    erties
    0.15
    inç
    0.14
    acct
    0.14
    Arrays
    0.14
     {{--<
    0.14
    reamble
    0.14
    obus
    0.14
    μη
    0.14
     waive
    0.13
    Act Density 0.014%

    No Known Activations