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

    Neuronpedia

    INDEX
    Explanations

    categorical references to numerical data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    guard
    -0.17
    REFERRED
    -0.16
    /helper
    -0.15
    forge
    -0.15
    ¤í
    -0.15
    (s
    -0.14
    al
    -0.14
    less
    -0.14
    273
    -0.14
    109
    -0.14
    POSITIVE LOGITS
    âĢ³
    0.43
    s
    0.43
    âĢ²
    0.41
    ï¸ı
    0.32
    /-
    0.27
    sand
    0.23
    -го
    0.23
    sheets
    0.23
    -й
    0.23
    sus
    0.22
    Act Density 0.243%

    No Known Activations