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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a temporary pause or delay in activity

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "until."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raid
    -0.77
    puff
    -0.75
    pour
    -0.74
    eas
    -0.72
    jac
    -0.70
    virt
    -0.67
    ek
    -0.67
    ault
    -0.66
    cart
    -0.66
    kiss
    -0.65
    POSITIVE LOGITS
     2024
    0.87
     2019
    0.81
     proven
    0.76
     2020
    0.75
     2021
    0.75
     midnight
    0.73
    omore
    0.72
    terday
    0.70
     adulthood
    0.69
     October
    0.67
    Act Density 0.030%

    No Known Activations