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

    Neuronpedia

    INDEX
    Explanations

    time-related references in the text

    oai_token-act-pair · gpt-3.5-turbo

    various phrases indicating approximate time durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    911
    -0.65
    alist
    -0.63
    matic
    -0.61
     Byrd
    -0.61
    anus
    -0.61
    2020
    -0.61
    smith
    -0.61
    work
    -0.61
    always
    -0.60
    protect
    -0.60
    POSITIVE LOGITS
    ugu
    0.76
    othes
    0.75
    oths
    0.71
    bered
    0.69
    =-=-=-=-
    0.67
    utra
    0.66
    ovych
    0.65
    apy
    0.65
    zin
    0.65
    rentices
    0.64
    Act Density 0.010%

    No Known Activations