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

    Neuronpedia

    INDEX
    Explanations

    instances of dialogue and punctuation in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     wel
    -0.16
     ú
    -0.15
     Ãļ
    -0.15
     wa
    -0.15
    pike
    -0.14
    ¸ı
    -0.14
    occo
    -0.14
    umb
    -0.14
    ahkan
    -0.14
    .viewer
    -0.13
    POSITIVE LOGITS
    -schema
    0.15
    asics
    0.15
    ramid
    0.14
    Щ
    0.14
    ạnh
    0.14
    .bed
    0.14
     Bed
    0.14
    -scrollbar
    0.13
    UNT
    0.13
    /schema
    0.13
    Act Density 0.096%

    No Known Activations