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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their uses in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    非常的
    -0.84
     I
    -0.80
     
    -0.74
    ↵
    -0.67
     is
    -0.66
    !!!
    -0.66
      
    -0.66
    很多的
    -0.65
     i
    -0.64
     dimana
    -0.63
    POSITIVE LOGITS
    ​—
    1.07
     дописавши
    1.06
     doubtnut
    1.02
     NDEBUG
    1.02
     ―――――
    1.01
    UserScript
    1.01
     freilich
    1.01
    0.99
     offenbar
    0.96
     PLWABN
    0.95
    Act Density 0.643%

    No Known Activations