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

    Neuronpedia

    INDEX
    Explanations

    references to age-appropriateness and levels of intensity in content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     gó
    -0.16
    öm
    -0.15
    æ¬ł
    -0.15
    asma
    -0.14
    undry
    -0.14
    Æ°Æ¡ng
    -0.14
     Stam
    -0.14
    ceptors
    -0.14
     bills
    -0.14
    emark
    -0.13
    POSITIVE LOGITS
     Ava
    0.16
    ı
    0.16
    IMIT
    0.15
    ä¸įäºĨ
    0.15
    Operation
    0.15
    imit
    0.15
    TOTYPE
    0.15
     younger
    0.14
    aina
    0.14
    èĩªæ²»
    0.14
    Act Density 0.092%

    No Known Activations