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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, specifically apostrophes and quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Feu
    -0.65
     back
    -0.58
    квар
    -0.56
     FontWeight
    -0.55
     Table
    -0.54
     chi̍t
    -0.54
     jag
    -0.54
    -
    -0.53
     Jacobsen
    -0.52
     pia
    -0.52
    POSITIVE LOGITS
     purpoſe
    0.94
     deſt
    0.94
     uſed
    0.93
     ſur
    0.93
     ſtate
    0.93
     ſub
    0.92
     myſelf
    0.90
     ſta
    0.90
     houſe
    0.89
     ainfi
    0.88
    Act Density 0.137%

    No Known Activations