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

    Neuronpedia

    INDEX
    Explanations

    mentions of large scale or significant events or actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "massive" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yer
    -0.91
    mates
    -0.83
    keeper
    -0.76
     Handler
    -0.75
    mate
    -0.75
    nob
    -0.74
    say
    -0.72
    Dialogue
    -0.72
    keepers
    -0.71
    pring
    -0.70
    POSITIVE LOGITS
     amounts
    1.08
     undertaking
    0.99
     influx
    0.96
     overhaul
    0.91
     quantities
    0.91
     earthqu
    0.91
     understatement
    0.86
     conglomer
    0.83
     swath
    0.83
     redistribution
    0.83
    Act Density 0.066%

    No Known Activations