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

    Neuronpedia

    INDEX
    Explanations

    references to the term "white" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lun
    -0.15
    ERRU
    -0.15
    jaw
    -0.15
    joy
    -0.15
     Robinson
    -0.15
    jos
    -0.14
    Aws
    -0.14
     compression
    -0.14
    CLUDING
    -0.14
    llib
    -0.14
    POSITIVE LOGITS
    esty
    0.16
     Ser
    0.15
    bben
    0.15
    cel
    0.15
    çĨŁ
    0.15
    iyat
    0.14
    samp
    0.14
    etter
    0.14
    gende
    0.14
    uede
    0.14
    Act Density 0.038%

    No Known Activations