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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to the degree or intensity of something

    oai_token-act-pair · gpt-3.5-turbo

    strong adjectives that describe significant attributes or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stories
    -1.01
    events
    -0.92
    units
    -0.89
    letters
    -0.87
    iddles
    -0.86
    measures
    -0.84
    friends
    -0.83
    aunts
    -0.82
    hops
    -0.82
    stocks
    -0.81
    POSITIVE LOGITS
     uptick
    1.19
     amount
    1.16
     dose
    1.06
     imbalance
    1.04
     shortage
    1.04
     increase
    1.03
     lack
    1.01
     influx
    1.00
     degree
    0.97
     rift
    0.96
    Act Density 0.201%

    No Known Activations