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

    Neuronpedia

    INDEX
    Explanations

    specific quantitative or evaluative terms indicating importance or consequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SSERT
    -0.17
     Arrow
    -0.17
    nda
    -0.17
    lesi
    -0.15
    ÏĦιο
    -0.15
    ãĥĥãĥĪ
    -0.14
    inski
    -0.14
    iren
    -0.14
    Arrow
    -0.14
    ntag
    -0.14
    POSITIVE LOGITS
    monic
    0.16
    важа
    0.16
    zw
    0.15
     ë´ī
    0.15
    ZW
    0.14
    awai
    0.14
    CTS
    0.14
    æĤ
    0.14
    ,{"
    0.14
    imin
    0.14
    Act Density 0.006%

    No Known Activations