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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases indicating degrees or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eki
    -0.14
     Northwestern
    -0.14
    CursorPosition
    -0.13
    mux
    -0.13
    rons
    -0.13
    raph
    -0.13
    ãģ£ãģı
    -0.13
     Nez
    -0.13
    Æ°á»Ľi
    -0.13
     Highlander
    -0.13
    POSITIVE LOGITS
     Cov
    0.25
     cov
    0.24
    cov
    0.21
    _cov
    0.19
     covariance
    0.19
     fitted
    0.18
     specification
    0.18
     nug
    0.17
     SCALE
    0.17
     defaulted
    0.17
    Act Density 0.000%

    No Known Activations