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

    Neuronpedia

    INDEX
    Explanations

    mathematical fractions and ratios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ATIO
    -0.17
    ãĥ³ãĥĨ
    -0.16
    èµ·æĿ¥
    -0.15
    uden
    -0.14
    otomy
    -0.14
    entr
    -0.14
    iant
    -0.14
     rodin
    -0.13
     taraf
    -0.13
    .jd
    -0.13
    POSITIVE LOGITS
    -than
    0.21
     than
    0.18
    ovny
    0.15
    ulle
    0.15
    533
    0.15
     вÑģего
    0.15
     Twilight
    0.15
    687
    0.14
    OA
    0.14
    rer
    0.14
    Act Density 0.035%

    No Known Activations