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

    Neuronpedia

    INDEX
    Explanations

    names of locations, specifically "Ur" with varying numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific location or entity, likely related to "Urbana."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    女
    -0.79
     Sins
    -0.78
    washer
    -0.73
     Scarlet
    -0.70
     Dickinson
    -0.65
     Misc
    -0.64
     Phant
    -0.64
     sund
    -0.63
    eting
    -0.61
    iculty
    -0.61
    POSITIVE LOGITS
    gent
    1.15
    gencies
    1.01
    seless
    1.01
    du
    0.95
    gery
    0.94
    poses
    0.94
    gency
    0.93
    rah
    0.93
    geon
    0.91
    ged
    0.90
    Act Density 0.015%

    No Known Activations