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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and formatting symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    à¹Ģà¸ŀลà¸ĩ
    -0.14
    KHTML
    -0.14
    moth
    -0.14
     Cleanup
    -0.13
     odense
    -0.13
     env
    -0.13
    ãĥ¼ãĤ¸
    -0.13
    pter
    -0.13
    andalone
    -0.13
    OA
    -0.13
    POSITIVE LOGITS
    stands
    0.23
     acronym
    0.22
     abbreviation
    0.20
     initials
    0.20
    abbreviation
    0.19
     Metropolitan
    0.15
    reetings
    0.14
     Subscriber
    0.14
    ilities
    0.14
    rych
    0.14
    Act Density 0.039%

    No Known Activations