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

    Neuronpedia

    INDEX
    Explanations

    references to user instructions and requirements in technical or informative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    为äºĨ
    -0.19
    TriState
    -0.15
     длÑı
    -0.15
     Sexe
    -0.14
    lijah
    -0.14
    iggins
    -0.14
    ilha
    -0.14
    ILLE
    -0.14
     Äijá»ĥ
    -0.14
    rang
    -0.13
    POSITIVE LOGITS
    must
    0.16
     Must
    0.15
     resorts
    0.15
     must
    0.15
     resort
    0.14
    éľĢ
    0.14
    aris
    0.14
    é¡»
    0.14
    дем
    0.14
    инов
    0.14
    Act Density 0.218%

    No Known Activations