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

    Neuronpedia

    INDEX
    Explanations

    comments and annotations in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arna
    -0.15
    iras
    -0.15
    aign
    -0.15
    بÙĦ
    -0.14
    æ¸Ī
    -0.14
    inan
    -0.14
    cth
    -0.14
    rees
    -0.13
    ibs
    -0.13
    bud
    -0.13
    POSITIVE LOGITS
    ijke
    0.15
    âĺ
    0.15
    .consume
    0.14
    HWND
    0.14
    _REGS
    0.14
    罪
    0.14
     Sho
    0.13
     Schro
    0.13
    _escape
    0.13
    ergus
    0.13
    Act Density 0.006%

    No Known Activations