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

    Neuronpedia

    INDEX
    Explanations

    technical terms and variables related to programming and computational processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     möjligt
    -0.67
     tails
    -0.61
     TBS
    -0.60
     Tolstoy
    -0.60
     Zjednoc
    -0.58
     giudi
    -0.58
     TDC
    -0.58
     مشين
    -0.57
     Dostupné
    -0.57
     nipples
    -0.57
    POSITIVE LOGITS
     Gund
    1.10
     GS
    1.07
    Bronnen
    1.03
     gs
    0.99
     g
    0.96
     GV
    0.91
     GSC
    0.90
     GSA
    0.90
     Gad
    0.89
     GES
    0.88
    Act Density 2.029%

    No Known Activations