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

    Neuronpedia

    INDEX
    Explanations

    phrases related to unique ASCII characters and symbols

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific character or symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     shack
    -0.75
     scatter
    -0.71
     Babel
    -0.66
     bye
    -0.66
     Borders
    -0.65
     prejudice
    -0.65
     Belg
    -0.64
     obfusc
    -0.64
     multiplying
    -0.63
     OB
    -0.63
    POSITIVE LOGITS
    ı
    1.36
    Ń
    1.28
    £
    1.21
    ¬
    1.19
    ²
    1.17
    º
    1.16
    Ĵ
    1.13
    ¹
    1.13
    Ĭ
    1.09
    İ
    1.08
    Act Density 0.219%

    No Known Activations