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

    Neuronpedia

    INDEX
    Explanations

    periods and question marks, indicating the end of sentences and inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sez
    -0.17
    ient
    -0.15
    akis
    -0.15
    isku
    -0.15
    asket
    -0.15
    UnderTest
    -0.15
    ersistent
    -0.14
    zu
    -0.14
    είο
    -0.14
    empor
    -0.14
    POSITIVE LOGITS
    holm
    0.16
     Kral
    0.15
    erin
    0.14
    utin
    0.14
    oj
    0.14
    ewe
    0.14
    Å¡ti
    0.14
    etus
    0.13
    ëł¥ìĿĦ
    0.13
     alt
    0.13
    Act Density 0.009%

    No Known Activations