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

    Neuronpedia

    INDEX
    Explanations

    connections and features related to structural design and flow dynamics within systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fences
    -0.18
     fence
    -0.17
    _dw
    -0.16
    etim
    -0.16
    å¢Ļ
    -0.15
    632
    -0.15
     Walls
    -0.15
    consin
    -0.15
     poles
    -0.14
     Fence
    -0.14
    POSITIVE LOGITS
     spaces
    0.21
     open
    0.20
     openings
    0.19
     space
    0.19
    -entry
    0.18
     opened
    0.18
     Chambers
    0.18
     channel
    0.18
    -open
    0.18
    open
    0.18
    Act Density 0.127%

    No Known Activations