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

    Neuronpedia

    INDEX
    Explanations

    terms related to mathematical concepts and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aniem
    -0.17
     Moy
    -0.16
    _CONSOLE
    -0.14
    enco
    -0.14
    unc
    -0.14
     asympt
    -0.14
    pto
    -0.14
     bricks
    -0.14
    åı
    -0.14
     Increment
    -0.13
    POSITIVE LOGITS
     equilibrium
    0.29
     миним
    0.26
     min
    0.26
     max
    0.25
     saddle
    0.25
     minimum
    0.24
     макÑģим
    0.24
     solutions
    0.24
     extrem
    0.23
     optimum
    0.22
    Act Density 0.275%

    No Known Activations