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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "until" followed by a numeric value indicating the strength of waiting

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a delay or waiting period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aque
    -0.80
    Rated
    -0.75
    aird
    -0.72
    Tro
    -0.72
    chal
    -0.71
    adem
    -0.70
    Runner
    -0.70
    VP
    -0.69
    gp
    -0.68
    kg
    -0.68
    POSITIVE LOGITS
     adulthood
    0.75
    dinand
    0.74
    ptives
    0.73
     2019
    0.71
    teenth
    0.71
     2021
    0.70
    ippi
    0.70
    itures
    0.67
     2020
    0.67
     AFTER
    0.66
    Act Density 0.029%

    No Known Activations