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

    Neuronpedia

    INDEX
    Explanations

    concepts related to stability and instability in mathematical systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acle
    -0.14
    çĴĥ
    -0.14
     filesize
    -0.13
    emmel
    -0.13
    몬
    -0.13
    ãģ®ãģ«
    -0.13
     Tensor
    -0.13
    ánÃŃm
    -0.13
    measurement
    -0.13
    ContentSize
    -0.13
    POSITIVE LOGITS
     stable
    0.35
     saddle
    0.33
     bif
    0.33
     unstable
    0.32
     steady
    0.31
     solutions
    0.30
     stability
    0.29
    stable
    0.28
     sadd
    0.27
     instability
    0.27
    Act Density 0.129%

    No Known Activations