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

    Neuronpedia

    INDEX
    Explanations

    adverbs of certainty

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing conjecture or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    issy
    -0.82
    elight
    -0.81
    uctor
    -0.75
    iya
    -0.72
    ife
    -0.71
    lette
    -0.67
    ible
    -0.67
    endar
    -0.67
    gencies
    -0.67
    uality
    -0.67
    POSITIVE LOGITS
     quir
    0.74
    Ń·
    0.73
     misunder
    0.72
     underestimate
    0.71
     outwe
    0.70
    ©¶æ
    0.69
     ought
    0.66
     overest
    0.66
     owe
    0.66
     regret
    0.66
    Act Density 0.028%

    No Known Activations