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

    Neuronpedia

    INDEX
    Explanations

    references to physical openings or entrances in locations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    RIC
    -0.78
     Towns
    -0.63
    OPA
    -0.62
    OTUS
    -0.61
    juven
    -0.60
     rebuilding
    -0.59
    terday
    -0.59
     domestically
    -0.58
    hunt
    -0.57
    payers
    -0.56
    POSITIVE LOGITS
     window
    1.12
     windows
    1.10
     vents
    1.00
     lenses
    0.92
     doorway
    0.90
     holes
    0.89
     windshield
    0.89
     lens
    0.86
     glasses
    0.85
     curtains
    0.84
    Act Density 0.137%

    No Known Activations