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

    Neuronpedia

    INDEX
    Explanations

    various types of human activities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ixed
    -0.70
    ocard
    -0.69
    oiler
    -0.68
     passage
    -0.67
    Enough
    -0.66
    oning
    -0.63
     cracked
    -0.63
    uran
    -0.62
    Boss
    -0.62
    AU
    -0.61
    POSITIVE LOGITS
     activities
    1.02
    ional
    0.95
     undertaken
    0.89
    eering
    0.86
    ivism
    0.84
    rador
    0.80
    ational
    0.76
    anooga
    0.75
     activity
    0.75
     Activities
    0.73
    Act Density 0.028%

    No Known Activations