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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and special characters used in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edin
    -0.17
    olph
    -0.14
    Ø·Ùģ
    -0.14
     Sass
    -0.14
    ektör
    -0.14
    552
    -0.13
    ï½¥
    -0.13
    orie
    -0.13
     Vin
    -0.13
    cad
    -0.13
    POSITIVE LOGITS
    mn
    0.18
    ustr
    0.16
     mn
    0.15
     Witness
    0.14
    HEMA
    0.14
    ëłĪìĿ´
    0.13
    isoft
    0.13
     witness
    0.13
    MN
    0.13
     >č↵
    0.13
    Act Density 0.149%

    No Known Activations