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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of the universe

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     bParam
    -0.57
    dts
    -0.54
     tappa
    -0.53
     Goldman
    -0.52
    Mathieu
    -0.52
     Mittag
    -0.52
    NOSTIC
    -0.52
    eql
    -0.51
    tyn
    -0.50
    tagHelper
    -0.50
    POSITIVE LOGITS
     Universe
    1.34
     universes
    1.27
    Universe
    1.23
     UNIVER
    1.18
     universe
    1.16
     виправивши
    1.01
     Universo
    1.00
    universo
    0.97
    SequentialGroup
    0.95
    universe
    0.95
    Act Density 0.005%

    No Known Activations