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

    Neuronpedia

    INDEX
    Explanations

    numerical values or ranges related to time durations or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ebo
    -0.16
    ابÛĮ
    -0.14
    ingles
    -0.14
    anja
    -0.14
    352
    -0.14
    CEED
    -0.14
    arnation
    -0.14
    dirs
    -0.14
    stru
    -0.13
    abyrinth
    -0.13
    POSITIVE LOGITS
    amp
    0.17
    uzz
    0.16
    uel
    0.15
    wel
    0.14
    iat
    0.14
    Forgery
    0.14
    oland
    0.14
    oline
    0.13
    pline
    0.13
    ÑĤен
    0.13
    Act Density 0.079%

    No Known Activations