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

    Neuronpedia

    INDEX
    Explanations

    statistical success rates and percentages related to outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    629
    -0.15
    uye
    -0.15
    egan
    -0.14
    'gc
    -0.14
    oleon
    -0.14
    326
    -0.14
    ritten
    -0.14
    irable
    -0.14
    ORM
    -0.13
     Ye
    -0.13
    POSITIVE LOGITS
     (%)
    0.16
    outil
    0.16
    iedy
    0.15
    abyrin
    0.14
    edo
    0.14
    stairs
    0.14
    .datab
    0.14
    _chance
    0.14
    @brief
    0.14
    .Percent
    0.14
    Act Density 0.242%

    No Known Activations