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

    Neuronpedia

    INDEX
    Explanations

    people's names and specific entities in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    keywords and names associated with media and entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stretches
    -0.54
    )=
    -0.53
     mileage
    -0.51
     embodiments
    -0.51
     willpower
    -0.50
     refunds
    -0.49
     misconception
    -0.48
     :=
    -0.48
     proverb
    -0.48
     hiber
    -0.48
    POSITIVE LOGITS
    $.
    1.05
    +.
    0.94
    !.
    0.91
    >.
    0.86
    *.
    0.85
    _.
    0.85
     respectively
    0.80
    .[
    0.77
    .
    0.75
    .</
    0.73
    Act Density 0.780%

    No Known Activations