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

    Neuronpedia

    INDEX
    Explanations

    contractions of the words "is not"

    oai_token-act-pair · gpt-3.5-turbo

    negations expressed through the contraction "isn't" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ERG
    -0.83
    onym
    -0.79
     è£ıè
    -0.71
    stre
    -0.71
    çĶŁ
    -0.70
    onyms
    -0.69
    è¦ļéĨĴ
    -0.68
    èĪ
    -0.68
    onymous
    -0.68
    RON
    -0.67
    POSITIVE LOGITS
     necessarily
    1.12
     exactly
    1.04
     gotta
    0.97
     really
    0.94
     gonna
    0.92
     quite
    0.91
     anymore
    0.90
     even
    0.90
     EVEN
    0.85
     bluff
    0.83
    Act Density 0.094%

    No Known Activations