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

    Neuronpedia

    INDEX
    Explanations

    terms related to estimation and reporting inaccuracies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ियर
    -0.17
    ãĥ¼ãĤº
    -0.17
    iki
    -0.17
    leen
    -0.15
    CustomLabel
    -0.15
    ç²
    -0.14
     vý
    -0.14
    ;element
    -0.14
    ivable
    -0.14
    ixel
    -0.14
    POSITIVE LOGITS
     Rout
    0.16
    lie
    0.15
    oint
    0.14
    inen
    0.14
     lie
    0.14
    urch
    0.14
    ures
    0.14
    unte
    0.14
    false
    0.13
    rompt
    0.13
    Act Density 0.216%

    No Known Activations