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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political opinions and policy recommendations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    fortune
    -0.74
    76561
    -0.70
     Crazy
    -0.64
     whirlwind
    -0.62
    saw
    -0.61
     unlucky
    -0.60
     Guess
    -0.59
     Mini
    -0.58
    Adding
    -0.58
    culus
    -0.57
    POSITIVE LOGITS
     be
    1.32
     prevail
    1.18
     encompass
    1.13
     remain
    1.12
     belong
    1.12
     consist
    1.06
     occur
    1.06
     preclude
    1.04
     reflect
    1.04
     preced
    1.03
    Act Density 0.176%

    No Known Activations