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

    Neuronpedia

    INDEX
    Explanations

    references to academic sources and citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Exposed
    -0.16
    atak
    -0.16
    anean
    -0.16
    enou
    -0.15
    ennen
    -0.15
    asher
    -0.14
    atel
    -0.14
    anax
    -0.14
    annie
    -0.14
    алÑĮ
    -0.14
    POSITIVE LOGITS
    åŃĺæ¡£
    0.20
     CS
    0.18
    CS
    0.17
    ÅĻÃŃž
    0.16
     archived
    0.16
     باغ
    0.16
     retrieved
    0.16
    Ret
    0.16
    -check
    0.15
    ToFit
    0.15
    Act Density 0.013%

    No Known Activations