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

    Neuronpedia

    INDEX
    Explanations

    dates, percentages, and units of measurement

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical values and time periods related to various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    swer
    -0.81
    thur
    -0.80
    hof
    -0.79
    ospace
    -0.78
    igslist
    -0.77
    ĺħ
    -0.77
    ername
    -0.77
     ..........
    -0.77
    ngth
    -0.76
    yip
    -0.75
    POSITIVE LOGITS
     Medals
    0.76
     Nemesis
    0.76
     Competitive
    0.75
     Terran
    0.74
    Battle
    0.74
     Norris
    0.70
    Weapon
    0.70
     Radiant
    0.68
     Combat
    0.67
    ETF
    0.67
    Act Density 0.058%

    No Known Activations