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

    Neuronpedia

    INDEX
    Explanations

    specific symbols or forms of punctuation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific symbol or character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Guinness
    -0.75
     Nept
    -0.73
     sacrific
    -0.72
     Droid
    -0.70
     warp
    -0.70
     bye
    -0.70
     giveaway
    -0.70
     extermin
    -0.69
     Cyan
    -0.67
     cyan
    -0.66
    POSITIVE LOGITS
    £
    1.05
    CNN
    1.04
    ı
    1.01
    Į
    0.99
    ¢
    0.99
    ¹
    0.98
    ª
    0.98
    Trump
    0.97
    Pg
    0.96
    ®
    0.96
    Act Density 0.389%

    No Known Activations