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

    Neuronpedia

    INDEX
    Explanations

    proper nouns like people's names and place names

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods or durations within narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     IPM
    -0.60
     Powered
    -0.58
     Crunch
    -0.54
     overload
    -0.54
     0004
    -0.53
     Grizz
    -0.53
     giveaways
    -0.53
     Decay
    -0.52
     manufactures
    -0.52
     incentiv
    -0.52
    POSITIVE LOGITS
    çĶ°
    0.80
    married
    0.76
    æµ
    0.75
    thood
    0.70
     fame
    0.66
    ukemia
    0.63
    è£
    0.60
    bart
    0.60
    ع
    0.60
     Himself
    0.60
    Act Density 1.831%

    No Known Activations