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

    Neuronpedia

    INDEX
    Explanations

    terms related to formal written communication and agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awei
    -0.15
    aina
    -0.14
    ÏĢÏīÏĤ
    -0.14
    Ú¯ÙĪÙĨÙĩ
    -0.14
    /Index
    -0.14
    opi
    -0.14
    rai
    -0.14
    ullivan
    -0.14
    -beta
    -0.14
    redient
    -0.13
    POSITIVE LOGITS
    ndef
    0.16
    achat
    0.15
    &page
    0.15
    afc
    0.15
    ufen
    0.15
    ruz
    0.15
    ecess
    0.14
    bef
    0.14
    dfs
    0.14
    keh
    0.14
    Act Density 0.037%

    No Known Activations