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

    Neuronpedia

    INDEX
    Explanations

    concepts related to statistical distributions and laws in experimental data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     averages
    -0.14
     dovol
    -0.14
    ervlet
    -0.14
    abeth
    -0.14
     altogether
    -0.13
     swims
    -0.13
    abad
    -0.13
     damer
    -0.13
    æī
    -0.13
    alic
    -0.13
    POSITIVE LOGITS
     slope
    0.29
     linear
    0.29
     Slo
    0.27
     curve
    0.27
    -linear
    0.26
     Linear
    0.26
    linear
    0.25
     sigmoid
    0.25
    Linear
    0.24
    Curve
    0.24
    Act Density 0.278%

    No Known Activations