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

    Neuronpedia

    INDEX
    Explanations

    the word "data."

    oai_token-act-pair · gpt-3.5-turbo

    references to data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ModLoader
    -0.90
    aughs
    -0.78
    tone
    -0.75
    lich
    -0.70
    atom
    -0.69
    Interstitial
    -0.67
    inct
    -0.65
    aline
    -0.64
    anism
    -0.64
     imitation
    -0.60
    POSITIVE LOGITS
     compiled
    1.13
     collected
    1.04
     disag
    1.01
     collection
    0.91
     analyzed
    0.91
     gathered
    0.89
     analytics
    0.87
     obtained
    0.87
     available
    0.85
     grap
    0.84
    Act Density 0.084%

    No Known Activations