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

    Neuronpedia

    INDEX
    Explanations

    time-related information

    oai_token-act-pair · gpt-3.5-turbo

    references to duration or time intervals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ramid
    -1.00
    ortium
    -0.95
    riad
    -0.88
    igent
    -0.83
    uthor
    -0.83
    rim
    -0.82
    alis
    -0.78
    riks
    -0.77
    hid
    -0.76
    awan
    -0.75
    POSITIVE LOGITS
    frames
    1.13
    zone
    0.84
    frame
    0.82
     elapsed
    0.77
     stamps
    0.77
     zone
    0.75
     expectancy
    0.75
    days
    0.73
    outs
    0.73
     indoors
    0.73
    Act Density 0.057%

    No Known Activations