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

    Neuronpedia

    INDEX
    Explanations

    descriptions of items, particularly framed pictures and wall-hangings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    èĵ
    -0.17
    åľ
    -0.15
    elta
    -0.15
     roofing
    -0.14
    ounc
    -0.14
    ¡
    -0.14
    .bundle
    -0.14
    ä¸ĺ
    -0.14
    amera
    -0.14
    RTL
    -0.14
    POSITIVE LOGITS
     wall
    0.35
     hanging
    0.31
     hangs
    0.31
    wall
    0.29
     hung
    0.28
     hang
    0.28
    -wall
    0.26
     Wall
    0.26
    hang
    0.25
     Hang
    0.25
    Act Density 0.085%

    No Known Activations