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

    Neuronpedia

    INDEX
    Explanations

    specific formatting elements used in mathematical equations or notations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anga
    -0.16
    uchen
    -0.16
    uld
    -0.16
    oor
    -0.15
     _
    -0.14
    azz
    -0.14
    imi
    -0.14
    екÑĤÑĥ
    -0.14
     Blur
    -0.14
     Bottle
    -0.14
    POSITIVE LOGITS
    ph
    0.18
     vice
    0.18
    shape
    0.16
    656
    0.16
    602
    0.15
    [--
    0.14
     Vice
    0.14
    raison
    0.14
    uem
    0.14
    ernes
    0.14
    Act Density 0.016%

    No Known Activations