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

    Neuronpedia

    INDEX
    Explanations

    mathematical definitions and properties related to sets and measure theory

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mani
    -0.17
    hero
    -0.16
    713
    -0.15
    dek
    -0.14
     subdivision
    -0.14
    826
    -0.14
    echan
    -0.14
    382
    -0.14
    ä¸įå¾Ĺ
    -0.13
    preh
    -0.13
    POSITIVE LOGITS
     stands
    0.28
     stand
    0.28
    stands
    0.26
     stood
    0.25
    den
    0.23
    stand
    0.23
     refers
    0.23
     denotes
    0.22
     refer
    0.21
     referring
    0.20
    Act Density 0.090%

    No Known Activations