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

    Neuronpedia

    INDEX
    Explanations

    references to garage doors and their mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wort
    -0.19
    ered
    -0.17
    ountains
    -0.16
    ее
    -0.14
    .hl
    -0.14
    conde
    -0.14
     firefight
    -0.14
    帽
    -0.14
     Jug
    -0.13
    еÑĢж
    -0.13
    POSITIVE LOGITS
     garage
    0.38
     Garage
    0.35
     opener
    0.33
    gar
    0.31
    Gar
    0.30
     gar
    0.24
     GAR
    0.23
     Gar
    0.22
     tors
    0.21
    Remote
    0.20
    Act Density 0.008%

    No Known Activations