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

    Neuronpedia

    INDEX
    Explanations

    references to public policy, industry classifications, and issues concerning civil rights or regulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ideon
    -0.17
    enberg
    -0.15
     Berm
    -0.15
    ighton
    -0.15
     distance
    -0.14
     loin
    -0.14
    ision
    -0.14
    ãĥ³ãĥĶ
    -0.14
    æŁĦ
    -0.14
    ra
    -0.14
    POSITIVE LOGITS
    nek
    0.17
    entionPolicy
    0.16
     seedu
    0.16
    URES
    0.15
    'gc
    0.15
    بÙĪاسطة
    0.15
    "profile
    0.15
    ìķł
    0.15
     sokak
    0.14
    بش
    0.14
    Act Density 0.350%

    No Known Activations