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

    Neuronpedia

    INDEX
    Explanations

    mathematical concepts related to graph theory and topology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Arbit
    -0.14
    errated
    -0.14
    ampaign
    -0.13
    pecific
    -0.13
    insula
    -0.13
    andes
    -0.13
     Spatial
    -0.13
     improvised
    -0.13
    lined
    -0.13
     Specific
    -0.13
    POSITIVE LOGITS
     theoret
    0.28
     theory
    0.28
     property
    0.23
     functor
    0.23
     structure
    0.23
     spaces
    0.23
     decomposition
    0.23
     operator
    0.22
     operators
    0.22
     preserving
    0.21
    Act Density 0.200%

    No Known Activations