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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "in."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uly
    -0.17
    ná
    -0.17
    uai
    -0.17
    ecast
    -0.17
    atsu
    -0.17
    gary
    -0.16
    né
    -0.16
    aku
    -0.15
    ných
    -0.15
    vailability
    -0.15
    POSITIVE LOGITS
    GT
    0.17
    Ù¾ÛĮ
    0.15
    elp
    0.15
    POCH
    0.14
    kt
    0.14
    arm
    0.14
     tes
    0.14
    linger
    0.14
    art
    0.14
    808
    0.14
    Act Density 0.018%

    No Known Activations