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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and their components in formal proofs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dain
    -0.15
     Snyder
    -0.14
    úp
    -0.14
    ä¸Ī
    -0.14
    enko
    -0.13
    oint
    -0.13
    /Dk
    -0.13
    æijĺ
    -0.13
    ì¸
    -0.13
     infinity
    -0.13
    POSITIVE LOGITS
     since
    0.29
    since
    0.26
     by
    0.22
     Since
    0.21
    Since
    0.19
     depuis
    0.19
     easily
    0.18
     noting
    0.17
     seit
    0.17
     notice
    0.17
    Act Density 0.242%

    No Known Activations