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

    Neuronpedia

    INDEX
    Explanations

    text related to planning or executing events or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to plans involving organization or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     allegedly
    -0.73
     supposedly
    -0.67
     apparently
    -0.63
    Downloadha
    -0.63
    ighed
    -0.63
    rawled
    -0.62
    ĸļ
    -0.60
    pired
    -0.60
     sparked
    -0.60
     inexpl
    -0.59
    POSITIVE LOGITS
     tomorrow
    1.04
     ..."
    0.91
    )"
    0.85
     âĢ¦"
    0.83
     ['
    0.82
    ),"
    0.82
    )."
    0.80
     ourselves
    0.80
     hereafter
    0.80
    !"
    0.79
    Act Density 1.384%

    No Known Activations