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

    Neuronpedia

    INDEX
    Explanations

    specific formatting characters and patterns, including letters and punctuation in various contexts, possibly related to legal or structured documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ény
    -0.15
    batim
    -0.15
    embr
    -0.15
    zew
    -0.15
    ÅĪ
    -0.14
    hare
    -0.14
    onda
    -0.14
    ATE
    -0.14
    ãĥ«ãĥĪ
    -0.14
    icho
    -0.14
    POSITIVE LOGITS
    otts
    0.16
    ollo
    0.15
    -quote
    0.15
    MenuStrip
    0.15
    ellido
    0.15
    Friendly
    0.14
    RuleContext
    0.13
    237
    0.13
    isi
    0.13
    apl
    0.13
    Act Density 0.020%

    No Known Activations