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

    Neuronpedia

    INDEX
    Explanations

    instances where the phrase "no doubt" appears

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing certainty or belief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emetery
    -0.91
    aeper
    -0.74
    nect
    -0.69
    aeus
    -0.68
    ahime
    -0.67
    psey
    -0.67
    endar
    -0.66
    avorite
    -0.66
    eller
    -0.66
    ippy
    -0.65
    POSITIVE LOGITS
     whatsoever
    0.93
    worthiness
    0.76
     coerced
    0.74
    lessly
    0.74
     tempted
    0.70
     rightly
    0.66
    worthy
    0.66
     ORIG
    0.63
     concerning
    0.62
     satisfied
    0.62
    Act Density 0.012%

    No Known Activations