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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "capacity" in a text

    oai_token-act-pair · gpt-3.5-turbo

    references to "capacity" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aida
    -0.86
    roma
    -0.76
    scene
    -0.68
    uran
    -0.66
    bart
    -0.66
    rom
    -0.65
    isco
    -0.65
    erer
    -0.65
    lique
    -0.64
    ĸļ
    -0.64
    POSITIVE LOGITS
     capacities
    1.30
     capacity
    1.15
     Capacity
    0.99
     utilization
    0.96
    capacity
    0.88
    auga
    0.80
    encies
    0.78
     gaps
    0.76
     mismatch
    0.76
    ibilities
    0.75
    Act Density 0.037%

    No Known Activations