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

    Neuronpedia

    INDEX
    Explanations

    references to interior spaces or structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     interior
    -2.30
    interior
    -2.14
    Interior
    -2.06
     Interior
    -2.00
     INTERIOR
    -1.95
    INTERIOR
    -1.74
     interiors
    -1.60
     interiores
    -1.52
     intérieur
    -1.48
     interieur
    -1.37
    POSITIVE LOGITS
     Ham
    0.33
     J
    0.30
     I
    0.29
    ,
    0.28
     McK
    0.28
     F
    0.28
     Hend
    0.27
     rink
    0.27
     T
    0.27
     "
    0.27
    Act Density 0.003%

    No Known Activations