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

    Neuronpedia

    INDEX
    Explanations

    words related to daily routines or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to daily routines or occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aine
    -0.85
    holes
    -0.83
    dinand
    -0.78
    artisan
    -0.75
    eer
    -0.75
    itsch
    -0.73
    hole
    -0.71
     Ellis
    -0.70
    iland
    -0.70
    AMI
    -0.68
    POSITIVE LOGITS
    motion
    0.92
     daily
    0.91
     weekday
    0.88
     upkeep
    0.84
     routines
    0.84
     weekly
    0.83
     dose
    0.82
     intervals
    0.82
     conclud
    0.82
     nightly
    0.79
    Act Density 0.011%

    No Known Activations