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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and concepts related to ranking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mash
    -0.16
    оÑĩной
    -0.15
    ovu
    -0.15
     cond
    -0.15
    unnel
    -0.14
    ÑĢовиÑĩ
    -0.14
    xac
    -0.14
    ullo
    -0.14
    æĪ¦
    -0.14
    izen
    -0.13
    POSITIVE LOGITS
    ilet
    0.15
    OfWork
    0.14
    omics
    0.14
     Minute
    0.14
     Mountains
    0.14
    ë£Į
    0.14
    imes
    0.13
     Salman
    0.13
    _ctor
    0.13
    erra
    0.13
    Act Density 0.024%

    No Known Activations