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

    Neuronpedia

    INDEX
    Explanations

    demographics related to voter groups and their reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chet
    -0.16
    jÃŃm
    -0.15
    DOI
    -0.15
    ÑģÑĤвоÑĢ
    -0.15
    gui
    -0.15
    usra
    -0.14
    íĺ¸
    -0.14
     ÑĢаÑħ
    -0.14
    vida
    -0.14
    iants
    -0.14
    POSITIVE LOGITS
     loyal
    0.17
     loyalty
    0.17
     swing
    0.16
    emand
    0.16
     mobil
    0.15
    306
    0.15
     switches
    0.15
    loy
    0.15
     f
    0.15
     leakage
    0.14
    Act Density 0.046%

    No Known Activations