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

    Neuronpedia

    INDEX
    Explanations

    phrases or words containing the symbol ">" followed by "|" and "=" symbols

    oai_token-act-pair · gpt-3.5-turbo

    symbols or characters that represent various expressions or annotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Palest
    -0.72
     NEC
    -0.67
     interf
    -0.67
     mathemat
    -0.66
     seiz
    -0.65
     RIS
    -0.65
     Izan
    -0.64
     fortun
    -0.62
     Tanz
    -0.61
     Tek
    -0.61
    POSITIVE LOGITS
    Ļ
    1.33
    ª
    1.26
    ¡
    1.23
    ħ
    1.22
    ĸ
    1.17
    Ĵ
    1.14
    ¢
    1.13
    ij
    1.11
    Ń
    1.11
    ı
    1.10
    Act Density 0.345%

    No Known Activations