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

    Neuronpedia

    INDEX
    Explanations

    mathematical concepts related to categories and representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tib
    -0.17
     multin
    -0.15
    nonnull
    -0.15
    .mult
    -0.15
     Discipline
    -0.15
    ãİ
    -0.15
     Liberties
    -0.14
    /***/
    -0.14
    辺
    -0.14
    upos
    -0.14
    POSITIVE LOGITS
     derived
    0.28
     Derived
    0.25
    Derived
    0.24
     triang
    0.22
     perverse
    0.21
     Verd
    0.21
    derived
    0.21
     dg
    0.19
    -derived
    0.19
     hearts
    0.19
    Act Density 0.020%

    No Known Activations