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

    Neuronpedia

    INDEX
    Explanations

    terms related to regulatory and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roma
    -0.75
    mma
    -0.69
    undrum
    -0.67
    swer
    -0.63
    ramid
    -0.63
    .........
    -0.60
    ;;;;
    -0.60
    yssey
    -0.59
    ////
    -0.58
    cko
    -0.57
    POSITIVE LOGITS
     officials
    0.92
     advocates
    0.87
     programmers
    0.87
     planners
    0.87
     designers
    0.86
     proponents
    0.86
     administrators
    0.86
     negotiators
    0.85
     audiences
    0.85
     practitioners
    0.85
    Act Density 0.391%

    No Known Activations