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

    Neuronpedia

    INDEX
    Explanations

    references to personal pronouns and subjective experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ispens
    -0.15
    onga
    -0.15
    itoris
    -0.15
     Western
    -0.14
    ricks
    -0.14
    æŦ
    -0.14
    loff
    -0.14
     keyValue
    -0.14
    ä¼į
    -0.14
     Common
    -0.13
    POSITIVE LOGITS
    اÛĮØ´
    0.17
    ocket
    0.15
    ovel
    0.15
    olicy
    0.15
    419
    0.15
    ĶåĽŀ
    0.15
    _chi
    0.14
    urret
    0.14
    urrets
    0.14
     Alec
    0.14
    Act Density 0.083%

    No Known Activations