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

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making and choices

    oai_token-act-pair · gpt-3.5-turbo

    questions about options or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiActiveUnfocused
    -0.33
    elight
    -0.30
    tnc
    -0.30
    æł
    -0.29
    cest
    -0.28
     Whilst
    -0.28
    Secondly
    -0.28
    thouse
    -0.27
    Interstitial
    -0.27
    itan
    -0.26
    POSITIVE LOGITS
    —"
    0.35
     Dunham
    0.33
     Huck
    0.33
     BuzzFeed
    0.31
     Hawking
    0.31
     Freak
    0.30
     goddamn
    0.28
     Mets
    0.28
     Trump
    0.28
    —
    0.27
    Act Density 4.458%

    No Known Activations