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

    Neuronpedia

    INDEX
    Explanations

    mentions of things or concepts that are above average, exceptional, or extreme

    oai_token-act-pair · gpt-3.5-turbo

    descriptors related to varying types of normality and experiential quality, often contrasting ideals with realities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    clips
    -0.90
    hops
    -0.86
    rooms
    -0.84
     Cosponsors
    -0.84
    tracks
    -0.83
    IVERS
    -0.80
    ernels
    -0.80
    lees
    -0.79
    reports
    -0.79
     hearings
    -0.78
    POSITIVE LOGITS
     standpoint
    0.93
     chunk
    0.90
     person
    0.89
     piece
    0.88
     thing
    0.85
     subset
    0.81
     entity
    0.81
     ruler
    0.80
     amount
    0.80
     dime
    0.80
    Act Density 0.501%

    No Known Activations