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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and semicolons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ↵
    -1.59
     
    -1.39
    .
    -1.32
    ,
    -1.28
    <eos>
    -1.22
    ↵↵
    -1.13
      
    -1.04
     (
    -1.01
    ↵↵↵
    -0.97
     "
    -0.93
    POSITIVE LOGITS
     myſelf
    1.70
     itſelf
    1.63
    contentLoaded
    1.44
     Савезне
    1.43
     ―――――
    1.42
     Monfieur
    1.42
     doubtnut
    1.41
     EconPapers
    1.40
     Efq
    1.38
     Anſ
    1.36
    Act Density 0.239%

    No Known Activations