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

    Neuronpedia

    INDEX
    Explanations

    statistical data and figures regarding measurements or performance indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    allee
    -0.17
    agara
    -0.16
    ancel
    -0.15
     اÙĦØ¢
    -0.15
    ÛĮÙĩ
    -0.15
    enstein
    -0.14
    Å¡tÄĽ
    -0.14
    ersh
    -0.14
    acht
    -0.14
    itag
    -0.14
    POSITIVE LOGITS
     tent
    0.14
     Hoe
    0.14
     fiber
    0.14
    .strings
    0.13
    Banner
    0.13
    amed
    0.13
     Pact
    0.13
     sum
    0.13
     Zeus
    0.13
    ta
    0.13
    Act Density 0.040%

    No Known Activations