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

    Neuronpedia

    INDEX
    Explanations

    various types of punctuation and structural indicators in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    noinspection
    -0.14
    ĵĺ
    -0.14
    usc
    -0.13
    uer
    -0.13
    anson
    -0.13
    мÑĭ
    -0.13
    ida
    -0.13
    ẻ
    -0.13
    ãĤ¦ãĥĪ
    -0.12
     Luo
    -0.12
    POSITIVE LOGITS
    Slf
    0.16
    theless
    0.16
    rst
    0.15
    tics
    0.15
    ehr
    0.14
    Msp
    0.14
    oldem
    0.14
    ecko
    0.14
    ordion
    0.14
    INSERT
    0.14
    Act Density 0.907%

    No Known Activations