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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atur
    -0.16
    DI
    -0.15
    uche
    -0.15
    æ£
    -0.14
     Inform
    -0.14
    Inform
    -0.13
    574
    -0.13
    atten
    -0.13
    лаг
    -0.13
    ERO
    -0.13
    POSITIVE LOGITS
    âĶIJ
    0.14
     LAP
    0.14
    eses
    0.14
    lık
    0.13
    alin
    0.13
     státu
    0.13
    \Resource
    0.13
    labs
    0.13
    ãĥ¼ãĥª
    0.13
    ieur
    0.13
    Act Density 0.112%

    No Known Activations