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

    Neuronpedia

    INDEX
    Explanations

    references to specific time periods

    oai_token-act-pair · gpt-3.5-turbo

    references to recent time periods or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    holes
    -0.72
    adle
    -0.68
    ounters
    -0.66
    /#
    -0.63
    roots
    -0.63
    hess
    -0.62
    ansk
    -0.62
    bred
    -0.62
    ounter
    -0.61
    keye
    -0.61
    POSITIVE LOGITS
     week
    1.42
     month
    1.41
     year
    1.28
     night
    1.16
     summer
    1.08
     weekend
    1.08
     autumn
    1.00
     fall
    1.00
     decade
    0.98
     semester
    0.97
    Act Density 0.061%

    No Known Activations