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

    Neuronpedia

    INDEX
    Explanations

    words indicating doubt or uncertainty

    oai_token-act-pair · gpt-3.5-turbo

    words that indicate uncertainty or incompleteness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Emin
    -0.83
     Cosponsors
    -0.82
    çļ
    -0.71
    agents
    -0.71
    rather
    -0.68
     Might
    -0.68
    imoto
    -0.64
    UGH
    -0.64
    ILY
    -0.63
    ð
    -0.62
    POSITIVE LOGITS
     anymore
    0.80
     satisfactory
    0.80
     nor
    0.79
     accurate
    0.74
     sure
    0.73
     satisfied
    0.71
     convincing
    0.69
    eworthy
    0.69
    icable
    0.68
     flawless
    0.67
    Act Density 0.051%

    No Known Activations