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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and code structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oda
    -0.16
    _PO
    -0.16
    erah
    -0.15
    ãĥĭãĤ¢
    -0.15
    #@
    -0.15
    æķ¦
    -0.15
    atura
    -0.15
    åIJIJ
    -0.14
    íĬ¼
    -0.14
    accumulator
    -0.13
    POSITIVE LOGITS
    /doc
    0.16
    .parse
    0.15
    oped
    0.15
     é¦
    0.15
    ximity
    0.15
     split
    0.15
    osen
    0.15
     Split
    0.14
    Uvs
    0.14
    oup
    0.14
    Act Density 0.050%

    No Known Activations