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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and modifiers that indicate conjunction or contrast

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bris
    -0.15
    argins
    -0.15
    astle
    -0.15
     Bris
    -0.15
    untas
    -0.15
    utta
    -0.15
    Ïģη
    -0.14
    ãĥ³ãĥģ
    -0.14
    enis
    -0.14
    ÑģÑĤе
    -0.14
    POSITIVE LOGITS
    .setViewport
    0.15
    striction
    0.15
    -divider
    0.14
     é¹
    0.14
    ë¡ł
    0.14
     con
    0.14
    warts
    0.14
    itionally
    0.13
     MSM
    0.13
    ियत
    0.13
    Act Density 0.250%

    No Known Activations