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

    Neuronpedia

    INDEX
    Explanations

    time-related terms indicating future periods

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to time frames and durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.84
    nered
    -0.76
    ¬¼
    -0.71
     fallen
    -0.66
     deserted
    -0.64
    ¶æ
    -0.63
     Entered
    -0.62
    gotten
    -0.62
     broken
    -0.61
     testim
    -0.60
    POSITIVE LOGITS
    orate
    0.81
     onwards
    0.81
    lease
    0.75
    imester
    0.71
    frames
    0.71
    antically
    0.71
     TBA
    0.69
     hereafter
    0.68
    riages
    0.68
    antle
    0.67
    Act Density 0.077%

    No Known Activations