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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and references to individuals in specific scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¿
    -0.16
     Dün
    -0.15
    ×Ļ×
    -0.15
     spiele
    -0.14
    ln
    -0.14
    irt
    -0.14
    riere
    -0.14
    quisites
    -0.14
     Fuji
    -0.14
    isci
    -0.14
    POSITIVE LOGITS
    èĢħçļĦ
    0.16
    ager
    0.15
    owski
    0.15
    Ĥ
    0.15
    edReader
    0.15
     offsetof
    0.15
    edException
    0.15
    ÄŁÃ¼
    0.15
    éra
    0.15
    etleri
    0.14
    Act Density 0.007%

    No Known Activations