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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns followed by a strong emotion or action verb

    oai_token-act-pair · gpt-3.5-turbo

    pronouns indicating personal involvement or reference in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kang
    -0.64
    ²¾
    -0.60
    ational
    -0.59
    upp
    -0.56
     Hold
    -0.55
     Tayyip
    -0.55
    Ŀ
    -0.54
    advertisement
    -0.54
     Kills
    -0.54
    ophobic
    -0.54
    POSITIVE LOGITS
     reasoned
    0.69
    added
    0.66
    instead
    0.62
    dos
    0.60
    dinand
    0.60
    bra
    0.59
     nevertheless
    0.59
    enei
    0.59
     heirs
    0.59
    uggest
    0.59
    Act Density 0.504%

    No Known Activations