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

    Neuronpedia

    INDEX
    Explanations

    references to places or objects in a setting involving education or organized events

    oai_token-act-pair · gpt-3.5-turbo

    references to settings or environments, particularly related to gatherings or social spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Pacific
    -0.87
     Samoa
    -0.81
    uggest
    -0.77
    aclysm
    -0.75
    iliate
    -0.72
    azeera
    -0.70
    cest
    -0.70
    jiang
    -0.70
    eed
    -0.70
     Rebell
    -0.69
    POSITIVE LOGITS
     desks
    0.99
     floors
    0.96
     doors
    0.88
     entrances
    0.82
     seats
    0.81
     horizont
    0.80
     benches
    0.80
     floor
    0.79
     seating
    0.77
    tyard
    0.76
    Act Density 0.698%

    No Known Activations