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

    Neuronpedia

    INDEX
    Explanations

    combinations of words related to objects or concepts

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving the word "with."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itially
    -0.70
    press
    -0.67
     alone
    -0.64
    iance
    -0.62
    stem
    -0.61
    orah
    -0.61
    pressure
    -0.61
    liction
    -0.61
    fighter
    -0.60
    BUG
    -0.59
    POSITIVE LOGITS
     regard
    1.06
     regards
    1.05
    drawn
    1.04
    stood
    1.02
     impunity
    1.01
    draw
    0.85
     respect
    0.78
    trl
    0.70
     dignity
    0.69
    ĪĴ
    0.68
    Act Density 0.130%

    No Known Activations