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

    Neuronpedia

    INDEX
    Explanations

    specific programming constructs and technical elements within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erte
    -0.19
    ække
    -0.17
    iti
    -0.16
    lob
    -0.15
    rans
    -0.15
    ahas
    -0.14
    اÙģÙĩ
    -0.14
     Fold
    -0.14
    onto
    -0.14
    vik
    -0.14
    POSITIVE LOGITS
    .ReadString
    0.16
    .UIManager
    0.14
    zan
    0.14
    ê¶Į
    0.14
    oog
    0.14
    пиÑģание
    0.14
     Traditional
    0.13
     Hiá»ĩp
    0.13
    345
    0.13
    .attrs
    0.13
    Act Density 0.003%

    No Known Activations