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

    Neuronpedia

    INDEX
    Explanations

    descriptions of physical activities and settings

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of sensory experiences and environmental details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Topic
    -0.72
     Analyst
    -0.68
    Specifically
    -0.66
    Iss
    -0.66
     Franchise
    -0.65
    Executive
    -0.65
    Policy
    -0.64
    DonaldTrump
    -0.64
    Chair
    -0.63
     VMware
    -0.63
    POSITIVE LOGITS
     cla
    0.78
     climbers
    0.75
     dusk
    0.72
     pilgr
    0.72
     climbs
    0.68
    grim
    0.68
     crou
    0.68
     indoors
    0.67
     gul
    0.67
     roofs
    0.65
    Act Density 1.729%

    No Known Activations