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

    Neuronpedia

    INDEX
    Explanations

    mentions of achievements or performances in various forms of competition or training

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating performance statistics in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ernel
    -0.65
     Bunker
    -0.64
    sten
    -0.63
    roots
    -0.62
    Feed
    -0.61
    operator
    -0.61
    adium
    -0.60
    quartered
    -0.60
    20439
    -0.60
    DAQ
    -0.59
    POSITIVE LOGITS
     breakout
    1.30
     standout
    1.14
     sensational
    1.05
     stellar
    1.03
     productive
    1.00
     cameo
    0.98
     stint
    0.98
     terrific
    0.95
     season
    0.92
    worldly
    0.92
    Act Density 0.107%

    No Known Activations