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

    Neuronpedia

    INDEX
    Explanations

    phrases related to time factors, specifically indicating future durations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to long-term time periods and durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Released
    -0.61
     gist
    -0.59
     scout
    -0.58
     guiActiveUn
    -0.57
     hotline
    -0.56
     dropped
    -0.55
    ahi
    -0.54
     sear
    -0.54
     blew
    -0.54
     spiked
    -0.53
    POSITIVE LOGITS
     future
    1.02
     foreseeable
    1.01
     2020
    0.94
     hereafter
    0.93
     2024
    0.92
    term
    0.90
    future
    0.90
     2021
    0.90
     eternity
    0.89
     2050
    0.87
    Act Density 0.164%

    No Known Activations