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

    Neuronpedia

    INDEX
    Explanations

    references to societal structures and notions of authority or governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     grumpy
    -0.91
     cheeky
    -0.90
     backlit
    -0.90
     prioritise
    -0.88
     Iconic
    -0.87
     dodgy
    -0.87
     reinvent
    -0.85
     proactively
    -0.85
     picky
    -0.84
     interchang
    -0.84
    POSITIVE LOGITS
     dunque
    0.88
     asimismo
    0.87
     wherein
    0.85
     Moreover
    0.82
     lecz
    0.81
     Thus
    0.81
    Moreover
    0.80
     presently
    0.79
     perciò
    0.79
     således
    0.79
    Act Density 3.150%

    No Known Activations