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

    Neuronpedia

    INDEX
    Explanations

    elements describing architectural features of living spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥ©
    -0.16
    483
    -0.15
    éĴ
    -0.14
    967
    -0.14
    968
    -0.14
    illo
    -0.14
    dings
    -0.13
    fax
    -0.13
     essentials
    -0.13
     Ged
    -0.13
    POSITIVE LOGITS
     glass
    0.31
     windows
    0.28
     sliding
    0.26
    -windows
    0.26
     doors
    0.25
     sliders
    0.25
    windows
    0.24
     Glass
    0.24
    glass
    0.23
    Glass
    0.23
    Act Density 0.051%

    No Known Activations