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

    Neuronpedia

    INDEX
    Explanations

    references to authority, governance, and oversight

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .(*
    -0.60
    TagHelper
    -0.58
    uerdo
    -0.58
     WALTZ
    -0.58
    ="(
    -0.54
     RSSSF
    -0.52
     Paglinawan
    -0.52
     Parcelable
    -0.52
     LCCN
    -0.52
    ::_('
    -0.51
    POSITIVE LOGITS
     of
    0.95
    ของ
    0.82
     των
    0.70
    andaş
    0.70
     của
    0.69
     της
    0.67
     løpet
    0.67
    :✨
    0.63
     Spuren
    0.63
    følgelig
    0.62
    Act Density 1.375%

    No Known Activations