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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political controversy and extremism

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     mosqu
    -0.86
     satell
    -0.83
     extinguished
    -0.82
    ikuman
    -0.81
     glim
    -0.80
     defe
    -0.78
    ishable
    -0.76
     steady
    -0.76
     transition
    -0.76
     gobl
    -0.74
    POSITIVE LOGITS
     Additionally
    1.42
     Apparently
    1.40
     Furthermore
    1.40
     Specifically
    1.40
     According
    1.40
     Interestingly
    1.33
     Needless
    1.31
     Ironically
    1.31
     Moreover
    1.30
     Meanwhile
    1.30
    Act Density 0.768%

    No Known Activations