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

    Neuronpedia

    INDEX
    Explanations

    references to goodness or quality in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĤŃ
    -0.16
    Writes
    -0.15
     NotImplemented
    -0.15
    å¼ı
    -0.14
    ndon
    -0.14
    drv
    -0.14
    ÃŃk
    -0.14
     contrast
    -0.13
    ils
    -0.13
    itals
    -0.13
    POSITIVE LOGITS
    -quality
    0.15
     Halk
    0.14
    bye
    0.14
    bst
    0.14
    onec
    0.14
    ТÐŀ
    0.13
    dea
    0.13
    uzzer
    0.13
     disposed
    0.13
     League
    0.13
    Act Density 0.281%

    No Known Activations