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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical notations and operations related to functions and variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     möjligt
    -0.69
     Zjednoc
    -0.66
    prepareStatement
    -0.63
     Tolstoy
    -0.61
    ondra
    -0.60
     tails
    -0.59
     douceur
    -0.59
     giudi
    -0.58
    cils
    -0.57
     Ortsteil
    -0.57
    POSITIVE LOGITS
     Gund
    1.09
    Bronnen
    1.06
     GS
    0.98
     g
    0.95
     kasarigan
    0.93
     gs
    0.91
     GSC
    0.91
     GES
    0.90
     Gad
    0.88
     GSA
    0.88
    Act Density 1.304%

    No Known Activations