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

    Neuronpedia

    INDEX
    Explanations

    comparisons involving numerical values or thresholds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zia
    -0.15
    werk
    -0.15
    colo
    -0.14
    ssp
    -0.13
    439
    -0.13
     rounding
    -0.13
     Ball
    -0.13
    .LogError
    -0.13
    udur
    -0.13
    Ĺ
    -0.13
    POSITIVE LOGITS
    clc
    0.15
    erville
    0.15
    oucher
    0.15
    \Framework
    0.15
    ABCDE
    0.14
     habit
    0.14
    بش
    0.14
    ánd
    0.14
    690
    0.14
    éĹ
    0.14
    Act Density 0.037%

    No Known Activations