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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their representations within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DAQ
    -0.18
    iece
    -0.17
     Sat
    -0.17
    alles
    -0.16
    SAT
    -0.16
    Sat
    -0.16
     satur
    -0.16
    æ·»
    -0.16
    anni
    -0.15
    416
    -0.15
    POSITIVE LOGITS
    elf
    0.17
    elts
    0.15
    oton
    0.15
    αÏģά
    0.15
    Ń
    0.14
    íħIJ
    0.14
    xies
    0.14
    vern
    0.14
    cul
    0.14
    canf
    0.14
    Act Density 0.038%

    No Known Activations