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

    Neuronpedia

    INDEX
    Explanations

    references to interactive elements or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wyn
    -0.16
    enco
    -0.14
    raj
    -0.14
    nt
    -0.14
    ICY
    -0.14
    opies
    -0.14
    eyer
    -0.14
    /is
    -0.14
    raf
    -0.14
    amer
    -0.14
    POSITIVE LOGITS
    olson
    0.17
    RG
    0.15
    aÄįnÃŃ
    0.14
    yg
    0.14
    iture
    0.14
     participation
    0.14
    tiler
    0.14
    edd
    0.14
     Nath
    0.14
    orld
    0.13
    Act Density 0.013%

    No Known Activations