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

    Neuronpedia

    INDEX
    Explanations

    quantitative expressions, particularly those related to percentages and monetary values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    еÑģÑĤи
    -0.16
    jÃŃm
    -0.15
    STALL
    -0.15
    OUTH
    -0.15
     Ø´ÙħارÙĩ
    -0.14
    istické
    -0.14
    ervlet
    -0.14
    ledo
    -0.14
    íij¸
    -0.14
     numéro
    -0.14
    POSITIVE LOGITS
    iles
    0.33
     (%)
    0.31
     percent
    0.30
    ile
    0.28
    -plus
    0.26
    percent
    0.25
     of
    0.24
     chance
    0.24
    -percent
    0.24
     coverage
    0.23
    Act Density 0.073%

    No Known Activations