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

    Neuronpedia

    INDEX
    Explanations

    adverbs and phrases related to correctness or justification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ickey
    -0.16
     WCHAR
    -0.15
    rey
    -0.15
    Uvs
    -0.15
    tery
    -0.15
    LineColor
    -0.14
    antar
    -0.14
    εια
    -0.14
    arg
    -0.14
     ÐĹав
    -0.14
    POSITIVE LOGITS
    loub
    0.16
     {{↵
    0.15
     Tradable
    0.15
    963
    0.15
    vail
    0.14
     Verd
    0.14
     åİ
    0.14
    morgan
    0.14
    pent
    0.13
     kro
    0.13
    Act Density 0.193%

    No Known Activations