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

    Neuronpedia

    INDEX
    Explanations

    references to various types of activities or events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "activity" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uran
    -0.82
    gling
    -0.77
     passage
    -0.74
    Boss
    -0.71
    oiler
    -0.70
    haul
    -0.69
    ophe
    -0.68
    pper
    -0.67
    ocard
    -0.66
    ppers
    -0.66
    POSITIVE LOGITS
    ional
    0.95
     activity
    0.88
    ivism
    0.87
     Activity
    0.82
    ual
    0.82
    iveness
    0.81
    uality
    0.81
     activities
    0.80
    ivity
    0.80
     undertaken
    0.72
    Act Density 0.027%

    No Known Activations