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

    Neuronpedia

    INDEX
    Explanations

    connections and relationships represented by numbers and mathematical models

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aida
    -0.15
    iesel
    -0.15
    è§Ī
    -0.14
    amu
    -0.14
     Reich
    -0.13
    arton
    -0.13
    echan
    -0.13
    á»ĩn
    -0.13
    976
    -0.13
    iÄįe
    -0.13
    POSITIVE LOGITS
     represent
    0.54
    代表
    0.52
     represents
    0.51
    represent
    0.51
     representing
    0.50
    表示
    0.46
     Represent
    0.44
     Represents
    0.43
     representa
    0.40
     représ
    0.40
    Act Density 0.455%

    No Known Activations