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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, especially periods and commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     yourselves
    -0.14
     عÙĤ
    -0.13
    ascar
    -0.13
    Âłp
    -0.13
    Discovery
    -0.13
    xac
    -0.13
     ficken
    -0.13
    noinspection
    -0.13
     ret
    -0.12
     himself
    -0.12
    POSITIVE LOGITS
    holm
    0.15
    -wsj
    0.12
    <fieldset
    0.12
    ysz
    0.12
    erve
    0.12
    .googleapis
    0.12
    esterday
    0.12
    ãģķãĤī
    0.12
    ionale
    0.12
    odor
    0.12
    Act Density 0.038%

    No Known Activations