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

    Neuronpedia

    INDEX
    Explanations

    locations or descriptions of physical structures

    oai_token-act-pair · gpt-3.5-turbo

    details related to urban infrastructure and geographic locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umers
    -0.58
    Individual
    -0.58
    Versions
    -0.57
    Professional
    -0.54
    Specific
    -0.54
    Statistics
    -0.53
    CEO
    -0.52
    Americans
    -0.52
    ciating
    -0.52
    analy
    -0.52
    POSITIVE LOGITS
     courtyard
    1.12
     plaza
    1.11
     tunnels
    1.09
     driveway
    1.07
     stairs
    1.06
     gardens
    1.05
     caves
    1.03
     hills
    1.03
     cliffs
    1.03
     sidewalks
    1.03
    Act Density 0.969%

    No Known Activations