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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating certainty or confidence

    oai_token-act-pair · gpt-3.5-turbo

    expressions of certainty or lack of doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eller
    -0.85
    ellery
    -0.73
    emetery
    -0.72
    ebra
    -0.72
    uterte
    -0.71
    cler
    -0.70
    ells
    -0.69
    holder
    -0.69
    oiler
    -0.69
    ocket
    -0.68
    POSITIVE LOGITS
     whatsoever
    0.89
     coerced
    0.80
     tempted
    0.76
     rightly
    0.73
     spurred
    0.71
     provoked
    0.71
     prompted
    0.70
     exagger
    0.69
     underest
    0.69
     msec
    0.68
    Act Density 0.014%

    No Known Activations