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

    Neuronpedia

    INDEX
    Explanations

    words related to personal thoughts and experiences

    oai_token-act-pair · gpt-3.5-turbo

    expressions of uncertainty or self-doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    etheus
    -0.78
    merce
    -0.78
     bidder
    -0.73
    kefeller
    -0.72
    akedown
    -0.71
    lihood
    -0.67
     Auction
    -0.66
    zbollah
    -0.65
     pestic
    -0.65
     convoy
    -0.63
    POSITIVE LOGITS
    laughs
    1.04
     haha
    0.98
     understatement
    0.94
     cliché
    0.90
     kidding
    0.88
     joking
    0.87
     ðŁĺ
    0.87
     ðŁĻĤ
    0.86
     remembering
    0.86
     sarc
    0.85
    Act Density 0.584%

    No Known Activations