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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating actions or events that will happen in the future

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "later on."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     liter
    -0.76
     AUTH
    -0.72
    MIT
    -0.71
     Ming
    -0.70
    RL
    -0.65
    NSA
    -0.64
    Abstract
    -0.63
    CDC
    -0.62
    Jose
    -0.62
    SHARE
    -0.61
    POSITIVE LOGITS
    shore
    1.05
    etime
    0.96
    erous
    0.89
    side
    0.83
     Sundays
    0.80
     behalf
    0.79
    sight
    0.78
    coming
    0.77
     probation
    0.76
     Route
    0.75
    Act Density 0.064%

    No Known Activations