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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks that indicate dialogue or quoted speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -2.10
     Monfieur
    -2.00
     itſelf
    -1.99
     pleaſure
    -1.97
     Anſ
    -1.97
     ―――――
    -1.92
     Reſ
    -1.91
     Efq
    -1.91
     Theſe
    -1.80
     purpoſe
    -1.80
    POSITIVE LOGITS
     
    1.32
     “
    1.19
    ,
    1.12
    ↵
    1.09
     "
    1.00
      
    0.98
     (
    0.98
    <eos>
    0.98
    .
    0.97
     and
    0.96
    Act Density 0.155%

    No Known Activations