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

    Neuronpedia

    INDEX
    Explanations

    powerful adverbs that express certainty or high probability

    oai_token-act-pair · gpt-3.5-turbo

    words expressing certainty and confidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mour
    -0.67
    ylum
    -0.65
    hod
    -0.64
     doomed
    -0.63
     mats
    -0.59
     Mats
    -0.59
     Kus
    -0.59
     Respons
    -0.59
    ELD
    -0.58
    mails
    -0.58
    POSITIVE LOGITS
     afford
    1.29
     imagine
    1.05
     muster
    1.03
     manipulate
    1.01
     withstand
    1.00
     communicate
    0.95
     conceive
    0.95
     relate
    0.95
     handle
    0.95
     manage
    0.92
    Act Density 0.111%

    No Known Activations