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

    Neuronpedia

    INDEX
    Explanations

    questions and discussions related to personal preferences and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inde
    -0.15
    uba
    -0.15
    lun
    -0.15
     suff
    -0.14
    าะ
    -0.14
    ingles
    -0.13
    หม
    -0.13
     Pra
    -0.13
    ungkin
    -0.13
    ĨĴ
    -0.13
    POSITIVE LOGITS
     favourite
    0.21
     favorite
    0.21
    favorite
    0.18
     advice
    0.17
    Advice
    0.16
     Advice
    0.16
    令
    0.16
     guilty
    0.16
    Favorite
    0.15
    avourite
    0.15
    Act Density 0.132%

    No Known Activations