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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating an amount of time spent in a specific location

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "for" followed by numerical references to durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Introduced
    -0.67
    illin
    -0.66
    Ohio
    -0.65
    urred
    -0.65
    uckland
    -0.64
    KK
    -0.63
    fleet
    -0.63
    aults
    -0.62
    =>
    -0.61
    ´
    -0.61
    POSITIVE LOGITS
     awhile
    1.12
     instance
    1.08
     example
    1.03
    geries
    1.00
    bidden
    0.99
    gotten
    0.93
    aging
    0.88
     starters
    0.88
     months
    0.86
     purposes
    0.84
    Act Density 0.197%

    No Known Activations