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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and elements related to algebraic structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    couz
    -0.17
    yh
    -0.16
     echang
    -0.15
    usta
    -0.15
    veau
    -0.15
    ye
    -0.15
    zte
    -0.15
    ayo
    -0.15
    гаÑĶ
    -0.14
    gamber
    -0.14
    POSITIVE LOGITS
     m
    0.35
     k
    0.31
    k
    0.29
    n
    0.28
     kn
    0.28
    kn
    0.28
     n
    0.28
    m
    0.28
     r
    0.27
     l
    0.26
    Act Density 0.399%

    No Known Activations