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

    Neuronpedia

    INDEX
    Explanations

    references to significant or impactful events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "massive" indicating significant scale or impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yer
    -0.88
    gemony
    -0.71
    lest
    -0.71
    wick
    -0.70
    keeper
    -0.70
    tein
    -0.70
    wich
    -0.70
    alias
    -0.68
    arers
    -0.68
    keepers
    -0.68
    POSITIVE LOGITS
     amounts
    1.08
     earthqu
    0.98
     influx
    0.94
     undertaking
    0.93
     swath
    0.87
     proportions
    0.86
     quantities
    0.84
     chunk
    0.83
     overhaul
    0.83
     disproportion
    0.83
    Act Density 0.027%

    No Known Activations