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

    Neuronpedia

    INDEX
    Explanations

    references to parties or events

    oai_token-act-pair · gpt-3.5-turbo

    references to social gatherings or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    obic
    -0.77
    twitter
    -0.66
     Colt
    -0.66
     Marketable
    -0.65
    iary
    -0.65
     Bolt
    -0.64
    peria
    -0.63
     Stafford
    -0.63
    terday
    -0.62
    abe
    -0.62
    POSITIVE LOGITS
    goers
    1.18
    tail
    0.85
    room
    0.78
    cloth
    0.77
    Party
    0.74
    eering
    0.74
     gatherings
    0.73
    ratulations
    0.73
     favors
    0.72
     planner
    0.72
    Act Density 0.033%

    No Known Activations