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

    Neuronpedia

    INDEX
    Explanations

    concepts related to uniformity and distribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NewReader
    -0.53
     xlink
    -0.50
     John
    -0.49
    tagHelper
    -0.48
    withOpacity
    -0.47
    ANDUM
    -0.47
    Życiorys
    -0.47
     en
    -0.47
    uparrow
    -0.46
     Nilsson
    -0.46
    POSITIVE LOGITS
     evenly
    1.22
     équilibr
    0.89
     uniform
    0.86
     balanced
    0.85
    equal
    0.85
    uniform
    0.85
    Equal
    0.84
     uniformity
    0.81
     uneven
    0.81
    Uniform
    0.80
    Act Density 0.333%

    No Known Activations