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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing extremes or absolutes

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "absolute" and its variations, indicating a focus on the concept of absoluteness or extremity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    actionDate
    -0.98
    pocket
    -0.83
    NetMessage
    -0.81
    azine
    -0.78
    enegger
    -0.77
    bucks
    -0.77
    ioned
    -0.77
    spr
    -0.76
    acters
    -0.76
    kins
    -0.75
    POSITIVE LOGITS
     monarchy
    1.18
     monarch
    0.91
     majority
    0.89
     necessity
    0.88
     rarity
    0.83
     Zero
    0.82
     beginners
    0.82
     humidity
    0.80
     importance
    0.80
     pinnacle
    0.80
    Act Density 0.032%

    No Known Activations