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

    Neuronpedia

    INDEX
    Explanations

    occurrences of numeric values or parameters in formatted code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cwd
    -0.17
    Synopsis
    -0.16
    rif
    -0.16
    ermann
    -0.16
    ynet
    -0.14
    myp
    -0.14
    oom
    -0.14
    argas
    -0.14
    åħ¥ãĤĬ
    -0.14
    оже
    -0.13
    POSITIVE LOGITS
    urai
    0.16
    azo
    0.16
     int
    0.15
    zo
    0.15
    313
    0.14
    iken
    0.14
    rey
    0.13
    au
    0.13
     Bris
    0.13
     Mobil
    0.13
    Act Density 0.014%

    No Known Activations