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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and special characters in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,
    -0.52
     a
    -0.47
    lenburg
    -0.46
     an
    -0.46
     i
    -0.44
    hassee
    -0.44
    konto
    -0.43
    ⁢
    -0.43
     à
    -0.43
      
    -0.43
    POSITIVE LOGITS
     pleaſure
    1.25
     ſeveral
    1.23
     myſelf
    1.20
     Majefty
    1.19
     purpoſe
    1.18
     Houſe
    1.17
     Jefus
    1.10
     houſe
    1.10
     Conſ
    1.10
     greateſt
    1.09
    Act Density 0.442%

    No Known Activations