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

    Neuronpedia

    INDEX
    Explanations

    references to government and political authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     plum
    -0.17
    JR
    -0.16
    875
    -0.15
    rax
    -0.15
    430
    -0.14
     Sour
    -0.14
    .Abstract
    -0.14
     Aust
    -0.14
    .port
    -0.13
    wich
    -0.13
    POSITIVE LOGITS
    ãĥ¬ãĤ¹
    0.15
    hci
    0.15
     Khu
    0.15
    ãĥ³ãĥĶ
    0.14
    zap
    0.14
    _PY
    0.14
    oldown
    0.14
    ilename
    0.14
    outine
    0.14
    undry
    0.14
    Act Density 0.049%

    No Known Activations