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

    Neuronpedia

    INDEX
    Explanations

    punctuation and method syntax in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bbc
    -0.18
    wick
    -0.18
    ancel
    -0.15
    wang
    -0.15
    ãĥ¼ãĤ¹
    -0.14
    à¥Ģश
    -0.14
    ainter
    -0.14
    zych
    -0.14
    voke
    -0.14
    versed
    -0.14
    POSITIVE LOGITS
    IZER
    0.16
    idon
    0.15
    hra
    0.15
    329
    0.14
    uzzi
    0.14
    &id
    0.13
    ((&
    0.13
    uzz
    0.13
    IDA
    0.13
    -Cola
    0.13
    Act Density 0.004%

    No Known Activations