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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions related to functions and scaling laws

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Chwiliwch
    -0.42
     ब्रेकडाउन
    -0.35
     okru
    -0.35
    责编
    -0.33
     رد
    -0.33
    Sending
    -0.32
    PDU
    -0.31
    leyebilirsiniz
    -0.31
     разъ
    -0.31
    Moments
    -0.31
    POSITIVE LOGITS
     curve
    1.45
     curves
    1.34
    curve
    1.23
     slope
    1.18
     Curve
    1.15
     Curves
    1.14
    curves
    1.13
    Curve
    1.10
    Curves
    1.07
    slope
    1.06
    Act Density 2.185%

    No Known Activations