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

    Neuronpedia

    INDEX
    Explanations

    references to governmental policies or actions relating to immigration and sanctuary cities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    REE
    -0.84
    ï¸ı
    -0.80
    ANY
    -0.77
    wig
    -0.74
     Panther
    -0.68
     Saban
    -0.68
    driver
    -0.66
    llor
    -0.65
     Marketplace
    -0.65
     Peg
    -0.64
    POSITIVE LOGITS
    itary
    1.50
    ctuary
    1.48
    itized
    1.21
    ction
    1.11
    itiz
    1.10
    ufact
    1.10
    gha
    1.02
    cer
    0.97
    ct
    0.92
    ews
    0.92
    Act Density 0.023%

    No Known Activations