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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods and ellipses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     “
    -1.50
     
    -1.26
    ,
    -1.26
     "
    -1.23
     (
    -1.18
    /
    -1.14
      
    -1.10
     or
    -1.03
    .
    -1.02
    :
    -1.01
    POSITIVE LOGITS
     Efq
    2.71
    ).'
    2.65
     myſelf
    2.48
     ?'
    2.42
     itſelf
    2.38
     Monfieur
    2.34
    )':
    2.30
    .’”
    2.29
     !'
    2.28
    )'
    2.27
    Act Density 0.230%

    No Known Activations