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

    Neuronpedia

    INDEX
    Explanations

    details or specifics in sentences

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a reluctance to provide detailed information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     snapped
    -0.65
    HUD
    -0.62
    orest
    -0.61
    wine
    -0.61
    Located
    -0.61
     tapped
    -0.60
     sensed
    -0.60
     Located
    -0.59
     deposited
    -0.59
    alties
    -0.57
    POSITIVE LOGITS
     spoilers
    1.38
     specifics
    1.29
     details
    1.06
     spoiler
    1.04
     particulars
    1.04
     detail
    1.02
     too
    0.96
     rant
    0.92
     exhaustive
    0.90
     elabor
    0.90
    Act Density 0.300%

    No Known Activations