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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and specific formatting characters in text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    .
    -0.63
     (
    -0.61
    ↵↵
    -0.56
     “
    -0.56
    (
    -0.53
     &
    -0.52
    ,
    -0.52
    ↵
    -0.51
    e
    -0.50
     
    -0.49
    POSITIVE LOGITS
     Theſe
    1.32
     myſelf
    1.28
     Efq
    1.27
     himſelf
    1.21
     ainfi
    1.18
     becauſe
    1.15
     Jefus
    1.15
     ſeveral
    1.15
     Majefty
    1.14
     againſt
    1.13
    Act Density 0.565%

    No Known Activations