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

    Neuronpedia

    INDEX
    Explanations

    references to structures or buildings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pêche
    -0.79
     pitié
    -0.78
     noires
    -0.75
     espirituales
    -0.73
     ambientales
    -0.72
     côtes
    -0.69
     Vrij
    -0.69
     priestly
    -0.68
     faveur
    -0.68
     persino
    -0.67
    POSITIVE LOGITS
     building
    1.68
     buildings
    1.68
     Buildings
    1.50
    Buildings
    1.50
     Building
    1.49
    buildings
    1.45
    building
    1.43
    Building
    1.38
     BUILDING
    1.25
     BUILDINGS
    1.18
    Act Density 0.039%

    No Known Activations