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

    Neuronpedia

    INDEX
    Explanations

    the word "until" followed by a time indicator or event

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "until" and related temporal phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acus
    -0.78
    jac
    -0.76
    esta
    -0.74
    adem
    -0.73
    Sit
    -0.72
    Throw
    -0.71
    abet
    -0.69
    arious
    -0.68
    Ľ
    -0.66
    aque
    -0.66
    POSITIVE LOGITS
     2021
    1.26
     2019
    1.23
     2024
    1.15
     2022
    1.14
     2020
    1.14
     2025
    1.13
     2030
    1.10
     October
    1.06
     January
    1.06
     July
    1.05
    Act Density 0.048%

    No Known Activations