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

    Neuronpedia

    INDEX
    Explanations

    special characters or punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    instances of special characters or symbols within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tek
    -0.71
     Tob
    -0.62
     Targ
    -0.61
     Sok
    -0.61
     Strat
    -0.61
     Synd
    -0.60
    enegger
    -0.59
     Niet
    -0.59
     Zup
    -0.58
     Jem
    -0.58
    POSITIVE LOGITS
    Ļ
    1.69
    ¬
    1.38
    ĸ
    1.30
    ª
    1.28
    Ń
    1.27
    ľ
    1.25
    ı
    1.23
    ķ
    1.23
    ¤
    1.21
    µ
    1.21
    Act Density 0.408%

    No Known Activations