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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and sentence boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.84
     G
    -0.73
     '
    -0.73
     K
    -0.73
     time
    -0.70
     F
    -0.68
     A
    -0.68
     I
    -0.68
     P
    -0.68
     R
    -0.67
    POSITIVE LOGITS
     Monfieur
    1.41
     ainfi
    1.38
     myſelf
    1.33
     étoient
    1.32
    .,
    1.29
     avoient
    1.29
     ſtate
    1.22
     hunne
    1.22
     pleaſure
    1.22
     himſelf
    1.21
    Act Density 0.096%

    No Known Activations