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

    Neuronpedia

    INDEX
    Explanations

    components related to decoration and aesthetics in living spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Extr
    -0.16
     roofing
    -0.15
    æ³Ĭ
    -0.15
    ä¸ĺ
    -0.15
    /ic
    -0.14
    vil
    -0.14
     ÑģÑĤол
    -0.14
    loor
    -0.14
    ----------------------------------------------------------------------
    -0.13
    noch
    -0.13
    POSITIVE LOGITS
     hangs
    0.27
     hung
    0.26
     wall
    0.25
     hanging
    0.24
    wall
    0.23
     hang
    0.22
    hung
    0.21
    -wall
    0.21
    æĮĤ
    0.19
     Wall
    0.19
    Act Density 0.207%

    No Known Activations