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

    Neuronpedia

    INDEX
    Explanations

    references to positive attributes or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulia
    -0.16
    istrovstvÃŃ
    -0.15
    tre
    -0.15
    ateur
    -0.15
    à¸łà¸²à¸ŀ
    -0.15
    .AutoScaleMode
    -0.14
    reshold
    -0.14
    TD
    -0.14
    _roll
    -0.14
    ugin
    -0.14
    POSITIVE LOGITS
    ITIVE
    0.19
    graduate
    0.19
    sum
    0.18
    itivity
    0.17
    assium
    0.17
    greSQL
    0.17
     Pos
    0.17
    =pos
    0.17
    ibilities
    0.17
    gresql
    0.17
    Act Density 0.020%

    No Known Activations