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

    Neuronpedia

    INDEX
    Explanations

    instances of code-related keywords and structures, particularly in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AFX
    -0.16
    -of
    -0.15
    owan
    -0.15
    ughty
    -0.15
    eah
    -0.14
    acock
    -0.14
    ugh
    -0.14
    ären
    -0.14
    lier
    -0.14
    aday
    -0.14
    POSITIVE LOGITS
    utsche
    0.15
    bone
    0.14
    etine
    0.14
    İ
    0.14
     Raf
    0.14
     âĹĦ
    0.14
     Hammond
    0.14
    tid
    0.13
    ØŃÙĩ
    0.13
     Thornton
    0.13
    Act Density 0.002%

    No Known Activations