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

    Neuronpedia

    INDEX
    Explanations

    references to ongoing processes or recurring themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ignum
    -0.15
    .epam
    -0.15
    æŀ¶
    -0.15
    ãĥ³ãĤº
    -0.14
    illon
    -0.14
    oola
    -0.14
    atchet
    -0.14
    ÑĤап
    -0.14
    _FF
    -0.14
    ork
    -0.14
    POSITIVE LOGITS
    ogn
    0.15
     beh
    0.14
     Bek
    0.14
    ynos
    0.14
     Mapping
    0.14
     {-
    0.13
     thrott
    0.13
    lemn
    0.13
     feat
    0.13
    ÑĢаз
    0.13
    Act Density 0.131%

    No Known Activations