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

    Neuronpedia

    INDEX
    Explanations

    verbs indicating authoritative statements or guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ç±į
    -0.14
    ftware
    -0.14
    .Cond
    -0.14
    ÑĢеÑħ
    -0.13
    ona
    -0.13
    ZY
    -0.13
     Gib
    -0.13
     Dann
    -0.13
    herits
    -0.13
    ink
    -0.13
    POSITIVE LOGITS
    eton
    0.15
    isposable
    0.15
    οÏģ
    0.15
    ิà¸Ļà¸Ĺร
    0.14
     thôi
    0.14
    oppable
    0.14
    èĦ
    0.14
    ipple
    0.14
    atty
    0.14
    abis
    0.14
    Act Density 0.066%

    No Known Activations