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

    Neuronpedia

    INDEX
    Explanations

    special characters and formatting elements in code comments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Enumeration
    -0.15
    edar
    -0.15
    hurst
    -0.14
    ig
    -0.14
    ë£
    -0.13
     Mai
    -0.13
     Nor
    -0.13
    -hooks
    -0.13
     Hack
    -0.13
     Prec
    -0.13
    POSITIVE LOGITS
    afone
    0.18
    iveau
    0.16
    idlo
    0.15
    ãĥ©ãĥ³ãĥī
    0.15
    INET
    0.15
    erosis
    0.14
    uset
    0.14
    amd
    0.14
    å·®
    0.14
    aÅŁ
    0.14
    Act Density 0.046%

    No Known Activations