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

    Neuronpedia

    INDEX
    Explanations

    references to credibility and qualifications in relationships or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uko
    -0.14
    orr
    -0.14
    صÙĨ
    -0.14
    leen
    -0.13
    عÙĨÙĪاÙĨ
    -0.13
     pac
    -0.13
     sn
    -0.13
    ohn
    -0.13
    dbo
    -0.13
    åĿ¡
    -0.13
    POSITIVE LOGITS
    RAIN
    0.18
    iquer
    0.17
    rain
    0.16
    iffin
    0.15
    rush
    0.15
    tü
    0.14
    orgeous
    0.14
    .showMessage
    0.14
    alley
    0.14
    iku
    0.14
    Act Density 0.009%

    No Known Activations