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

    Neuronpedia

    INDEX
    Explanations

    references to two-dimensional and three-dimensional representations or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ../../../
    -0.30
    ../../
    -0.24
    fold
    -0.23
    ../
    -0.21
    ante
    -0.17
    th
    -0.17
    laus
    -0.16
    ../../../../
    -0.15
    ingly
    -0.15
    fall
    -0.15
    POSITIVE LOGITS
    nd
    0.59
    -thirds
    0.38
    nds
    0.33
    gether
    0.32
    ï¸ı
    0.29
    ND
    0.28
     dozen
    0.28
     thirds
    0.27
    /th
    0.26
     nd
    0.25
    Act Density 0.374%

    No Known Activations