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

    Neuronpedia

    INDEX
    Explanations

    quotes or string literals in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -1.39
    ,
    -1.36
    ↵
    -1.32
     
    -1.24
    <eos>
    -1.13
      
    -1.08
    ↵↵
    -1.04
    ?
    -1.02
    :
    -1.02
     (
    -1.02
    POSITIVE LOGITS
     myſelf
    1.86
     itſelf
    1.83
     Paglinawan
    1.79
     Савезне
    1.70
     resourceCulture
    1.66
     ―――――
    1.63
    ſelves
    1.58
     Jefus
    1.55
     doubtnut
    1.54
     Theſe
    1.54
    Act Density 0.286%

    No Known Activations