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

    Neuronpedia

    INDEX
    Explanations

    references to officials and officialdom in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nez
    -0.17
    fall
    -0.17
    ohl
    -0.16
    ings
    -0.16
    ply
    -0.15
    LF
    -0.15
    PLY
    -0.15
    igua
    -0.14
    asser
    -0.14
    atters
    -0.14
    POSITIVE LOGITS
    dom
    0.21
    dehyde
    0.20
    ivec
    0.19
    /legal
    0.17
    ÙĤات
    0.16
    844
    0.16
    /admin
    0.16
    ahoma
    0.15
    stration
    0.15
    ity
    0.14
    Act Density 0.019%

    No Known Activations