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

    Neuronpedia

    INDEX
    Explanations

    references to online encyclopedic sources and citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     untranslated
    -0.16
     trùng
    -0.15
     rapor
    -0.15
     åł
    -0.14
    ATIO
    -0.14
    ContextHolder
    -0.14
    igm
    -0.14
    ÃŃc
    -0.14
    iloc
    -0.13
     unp
    -0.13
    POSITIVE LOGITS
     enc
    0.45
    Enc
    0.41
     Enc
    0.39
     Encyclopedia
    0.39
     encyclopedia
    0.39
    ency
    0.35
     entry
    0.32
    _Enc
    0.31
    .Enc
    0.29
     Britann
    0.29
    Act Density 0.085%

    No Known Activations