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

    Neuronpedia

    INDEX
    Explanations

    letters and characters used in various contexts, particularly capital letters and punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tempts
    -0.18
     hâl
    -0.16
    byss
    -0.16
    ÙĨÙħ
    -0.14
    edom
    -0.14
    odore
    -0.14
    oland
    -0.14
    otre
    -0.14
    ynos
    -0.14
    teg
    -0.13
    POSITIVE LOGITS
    ĶåĽŀ
    0.15
    .TextInput
    0.14
    permit
    0.14
    aeda
    0.14
    AML
    0.14
    ystate
    0.13
    chwitz
    0.13
    ccd
    0.13
    esp
    0.13
    aN
    0.13
    Act Density 0.220%

    No Known Activations