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

    Neuronpedia

    INDEX
    Explanations

    questions or requests for information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "asked."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    marine
    -0.82
    ordinate
    -0.75
    pite
    -0.70
    xon
    -0.66
    Charge
    -0.64
     Tigers
    -0.63
    commit
    -0.62
     Difference
    -0.60
    photos
    -0.59
    sequent
    -0.59
    POSITIVE LOGITS
     rhet
    1.19
     asked
    1.15
     questions
    0.94
     asks
    0.94
    govtrack
    0.93
    naires
    0.92
     questioned
    0.87
     asking
    0.86
    FontSize
    0.86
    erville
    0.84
    Act Density 0.030%

    No Known Activations