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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or requests for help

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adas
    -0.14
    loh
    -0.14
    ListComponent
    -0.14
    344
    -0.14
     Shed
    -0.14
    é¤
    -0.13
    wayne
    -0.13
    idd
    -0.13
    eck
    -0.13
    ella
    -0.13
    POSITIVE LOGITS
    conde
    0.15
     kaydet
    0.14
    ipar
    0.14
    kea
    0.14
    inform
    0.14
    ANS
    0.14
    ofire
    0.14
    inke
    0.14
    GGLE
    0.13
    för
    0.13
    Act Density 0.114%

    No Known Activations