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

    Neuronpedia

    INDEX
    Explanations

    expressions related to the concept of "smallness" or "slightness."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AutoScaleMode
    -0.64
    ExecuteReader
    -0.62
    Endless
    -0.60
     незавершена
    -0.58
    makeConstraints
    -0.57
     Wyd
    -0.57
     '\\
    -0.55
    APIView
    -0.54
     Endless
    -0.54
     
    -0.53
    POSITIVE LOGITS
     bit
    0.96
     Etwas
    0.91
    Somewhat
    0.91
     trochę
    0.90
     slightly
    0.89
    extAlignment
    0.88
     کمی
    0.87
     المعيارى
    0.87
    slightly
    0.86
    Slightly
    0.86
    Act Density 0.080%

    No Known Activations