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

    Neuronpedia

    INDEX
    Explanations

    references to buildings and architectural features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     espirituales
    -0.70
     atonement
    -0.68
     faveur
    -0.68
     pêche
    -0.67
    XtraReports
    -0.67
     kebun
    -0.67
     côtes
    -0.66
     sauvage
    -0.66
     ambientales
    -0.66
     artesanales
    -0.65
    POSITIVE LOGITS
     buildings
    1.94
     building
    1.82
     Buildings
    1.74
    buildings
    1.66
    Buildings
    1.64
     Building
    1.63
    building
    1.55
    Building
    1.48
     BUILDINGS
    1.46
     BUILDING
    1.41
    Act Density 0.060%

    No Known Activations