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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "come."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    аж
    -0.15
    egral
    -0.15
    imson
    -0.14
    ieux
    -0.14
    é
    -0.14
    κά
    -0.14
    galement
    -0.14
    umblr
    -0.13
    ursday
    -0.13
    uhl
    -0.13
    POSITIVE LOGITS
    alic
    0.15
    agate
    0.14
    ires
    0.14
    testdata
    0.14
    orage
    0.14
    Fmt
    0.13
     circuit
    0.13
     Mori
    0.13
    mighty
    0.13
    atrix
    0.13
    Act Density 0.087%

    No Known Activations