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

    Neuronpedia

    INDEX
    Explanations

    programming-related keywords and structures in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     noch
    -0.17
     nowhere
    -0.16
    éĤĦ
    -0.16
    still
    -0.15
     still
    -0.15
    è¿ĺæĺ¯
    -0.14
     ни
    -0.14
    ||↵
    -0.14
     STILL
    -0.14
    '||
    -0.14
    POSITIVE LOGITS
     and
    0.24
     :↵
    0.20
    :↵
    0.20
    emit
    0.19
    ():↵
    0.19
    :↵↵
    0.18
     or
    0.18
    :#
    0.18
     \↵
    0.17
    aeda
    0.17
    Act Density 0.022%

    No Known Activations