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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical sections and theorems within academic texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÙĤØ·
    -0.15
    ioni
    -0.14
    inç
    -0.14
    ë°ľ
    -0.14
    ulumi
    -0.14
    ekl
    -0.13
    리ìĬ¤
    -0.13
    ->$
    -0.13
    ãĥ³ãĥIJ
    -0.13
    δÎŃ
    -0.13
    POSITIVE LOGITS
    2
    0.43
    3
    0.42
    4
    0.40
    1
    0.37
    5
    0.35
    6
    0.35
    7
    0.33
    8
    0.30
    9
    0.29
    10
    0.24
    Act Density 0.318%

    No Known Activations