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

    Neuronpedia

    INDEX
    Explanations

    statements or opinions regarding current political events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     fortun
    -0.78
     Marketable
    -0.75
     smoot
    -0.71
     photoc
    -0.70
    ãĥ¼ãĥĨ
    -0.68
     pastry
    -0.66
     icing
    -0.66
     outl
    -0.66
     typew
    -0.66
     bes
    -0.66
    POSITIVE LOGITS
    Ļ
    1.58
    ¬
    1.19
    ħ
    1.14
    į
    1.11
    ª
    1.06
    Ĵ
    1.05
    ¤
    1.02
    £
    1.00
    µ
    0.99
    ·
    0.99
    Act Density 0.417%

    No Known Activations