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

    Neuronpedia

    INDEX
    Explanations

    key terms related to authority and compliance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bis
    -0.15
    orks
    -0.15
    ivic
    -0.14
     ãĤ±
    -0.14
    aket
    -0.14
    orz
    -0.14
    .templates
    -0.14
     ÑĩаÑģом
    -0.13
    ีà¹Ģà¸Ķ
    -0.13
    ird
    -0.13
    POSITIVE LOGITS
     le
    0.16
     Bart
    0.15
    oku
    0.14
    uling
    0.14
    ált
    0.14
     simpl
    0.14
    prog
    0.14
    olang
    0.13
    901
    0.13
     kok
    0.13
    Act Density 0.007%

    No Known Activations