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

    Neuronpedia

    INDEX
    Explanations

    tokens that signify significant achievements or successes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     common
    -0.47
    тельстве
    -0.46
    Hz
    -0.45
    padek
    -0.42
     TextStyle
    -0.42
     Hz
    -0.40
    ATAN
    -0.40
     Open
    -0.40
    طان
    -0.40
     open
    -0.40
    POSITIVE LOGITS
    CloseOperation
    0.82
    atisfactory
    0.78
    BufferException
    0.75
     satisfactory
    0.74
    колеп
    0.74
    KommentareTeilen
    0.74
     الحره
    0.72
     correctes
    0.72
     satisfactorily
    0.72
    :✨
    0.70
    Act Density 0.189%

    No Known Activations