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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a desire or action to revisit or return to a previous state or location

    oai_token-act-pair · gpt-3.5-turbo

    mentions of returning to previous points or origins

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orst
    -0.60
    rowd
    -0.57
     Consent
    -0.56
     Syndicate
    -0.56
    weather
    -0.55
    stood
    -0.55
     Us
    -0.53
     Sutherland
    -0.53
     headlines
    -0.53
     privilege
    -0.52
    POSITIVE LOGITS
    packing
    1.13
    stab
    1.05
    packs
    0.98
    gam
    0.98
    tracking
    0.98
    track
    0.92
    doors
    0.92
    wards
    0.87
    )=(
    0.85
    trace
    0.85
    Act Density 0.037%

    No Known Activations