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

    Neuronpedia

    INDEX
    Explanations

    dates and events mentioned in news articles

    oai_token-act-pair · gpt-3.5-turbo

    references to schedules and timelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     himself
    -0.80
     herself
    -0.76
     fors
    -0.71
     mach
    -0.70
     attent
    -0.69
     rig
    -0.68
     stomp
    -0.68
     dissu
    -0.67
     jealous
    -0.66
     antit
    -0.66
    POSITIVE LOGITS
    Tickets
    1.13
    Wednesday
    1.09
    Sources
    1.06
    Tuesday
    1.05
    Thursday
    1.02
    UPDATE
    1.00
    Officials
    1.00
    PHOTOS
    0.99
    Details
    0.97
    Friday
    0.94
    Act Density 0.705%

    No Known Activations