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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their contextual significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _closure
    -0.15
    RAM
    -0.14
    ramid
    -0.14
    .firebaseapp
    -0.14
     span
    -0.14
    .dimensions
    -0.14
    usch
    -0.14
    rame
    -0.14
    ĵ¨
    -0.14
    夢
    -0.13
    POSITIVE LOGITS
    0.17
    ouri
    0.16
    andest
    0.15
     coordinate
    0.14
    ozem
    0.14
    ITTE
    0.14
     Nisan
    0.14
    break
    0.14
    lique
    0.14
    ause
    0.13
    Act Density 0.049%

    No Known Activations