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

    Neuronpedia

    INDEX
    Explanations

    statements related to opinions and preferences in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ÄijÃłn
    -0.15
    isible
    -0.14
    lav
    -0.14
     meille
    -0.13
    #__
    -0.13
    лава
    -0.13
    .AspNet
    -0.13
     meilleurs
    -0.13
    adan
    -0.13
    ä¸ĭ载次æķ°
    -0.12
    POSITIVE LOGITS
     regular
    0.36
     medium
    0.32
    regular
    0.32
     Regular
    0.32
     normal
    0.31
     smaller
    0.29
    Regular
    0.29
     standard
    0.28
     non
    0.27
    medium
    0.27
    Act Density 0.189%

    No Known Activations