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

    Neuronpedia

    INDEX
    Explanations

    phrases related to tracking and recording different types of data

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to tracking and recording data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çīĪ
    -0.74
    geoning
    -0.74
     conclud
    -0.73
    medium
    -0.71
    urai
    -0.70
    starter
    -0.70
    erion
    -0.69
    aciously
    -0.68
    reau
    -0.67
    ourage
    -0.67
    POSITIVE LOGITS
     whereabouts
    1.04
     elapsed
    0.94
     transactions
    0.91
     trillions
    0.91
     billions
    0.88
     every
    0.87
     logged
    0.85
     births
    0.84
     progress
    0.83
     activities
    0.83
    Act Density 0.404%

    No Known Activations