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

    Neuronpedia

    INDEX
    Explanations

    capital letters 'K' followed by the number 9 or 10

    oai_token-act-pair · gpt-3.5-turbo

    the repeated mention of a specific character or entity denoted by the letter "K"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.86
    terday
    -0.78
     Marketable
    -0.76
    ãĥ¼ãĥĨ
    -0.67
    ãĤ£
    -0.67
    utics
    -0.65
     stems
    -0.64
     acknow
    -0.64
    Ø©
    -0.63
     constitu
    -0.61
    POSITIVE LOGITS
    won
    1.09
    EEP
    1.07
    oop
    1.07
    essel
    1.02
    ota
    1.00
    avan
    1.00
    ratom
    0.99
    ernels
    0.97
    oko
    0.97
    rieg
    0.96
    Act Density 0.042%

    No Known Activations