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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to memory, storage, and capacity

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "of" in various contexts related to measurements and specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.82
    heses
    -0.77
    cffffcc
    -0.76
    few
    -0.73
     Unsure
    -0.71
    render
    -0.69
    attribute
    -0.67
    abilities
    -0.65
    alias
    -0.64
     caric
    -0.63
    POSITIVE LOGITS
    icial
    0.73
     cumulative
    0.66
     extra
    0.64
     airspace
    0.64
     total
    0.61
     pounds
    0.61
     assorted
    0.59
     additional
    0.59
     precipitation
    0.59
     sunshine
    0.59
    Act Density 0.104%

    No Known Activations