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

    Neuronpedia

    INDEX
    Explanations

    references to authoritative power or control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ening
    -0.16
    coe
    -0.15
    ήÏĤ
    -0.15
    ery
    -0.15
    ุà¸Ļ
    -0.15
    stagram
    -0.14
     hạng
    -0.14
    رÙĪØ·
    -0.14
    quel
    -0.14
    د
    -0.14
    POSITIVE LOGITS
    fully
    0.19
    ship
    0.17
    ment
    0.15
        ↵    ↵
    0.15
    ndef
    0.15
    forth
    0.15
    ìĦľëĬĶ
    0.15
    prising
    0.15
    /legal
    0.15
    ful
    0.15
    Act Density 0.057%

    No Known Activations