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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating clarity or certainty

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating clarity or emphasis in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Topics
    -0.70
    soDeliveryDate
    -0.64
     collaborations
    -0.59
     Canaver
    -0.58
    rf
    -0.55
     nets
    -0.55
     stunts
    -0.55
    hov
    -0.54
     halves
    -0.54
     Reincarn
    -0.53
    POSITIVE LOGITS
     abundantly
    1.43
     clear
    1.35
     evident
    1.23
     apparent
    1.21
     obvious
    1.21
     know
    1.13
     known
    1.08
    know
    1.06
     painfully
    1.05
    clear
    1.01
    Act Density 0.644%

    No Known Activations