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

    Neuronpedia

    INDEX
    Explanations

    adverbs conveying certainty or likelihood

    oai_token-act-pair · gpt-3.5-turbo

    words indicating certainty or likelihood

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ordable
    -0.77
    aughtered
    -0.71
    entary
    -0.71
     Starts
    -0.71
    "},
    -0.68
    cart
    -0.67
    accompan
    -0.66
    ourney
    -0.63
    heast
    -0.62
    aturdays
    -0.62
    POSITIVE LOGITS
     intent
    1.08
     sympath
    1.07
     regret
    1.06
     intend
    1.05
     regrets
    0.98
     unaware
    0.97
     sincere
    0.97
     misunderstood
    0.96
     intending
    0.96
     misunderstanding
    0.96
    Act Density 0.400%

    No Known Activations