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

    Neuronpedia

    INDEX
    Explanations

    phrases or words indicating moral judgment or correctness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idor
    -0.14
    ĤŃ
    -0.14
    /Documents
    -0.14
     Kah
    -0.14
    ils
    -0.14
    oring
    -0.14
     Implicit
    -0.14
    лÑĸд
    -0.14
    ết
    -0.13
    ignKey
    -0.13
    POSITIVE LOGITS
    quartered
    0.16
    fully
    0.14
    ipe
    0.14
    ãĥªãĤ«
    0.14
    ÑijÑĢ
    0.13
    ume
    0.13
    dden
    0.13
    immel
    0.13
    ayers
    0.13
    une
    0.13
    Act Density 0.013%

    No Known Activations