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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific countries and political events

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, primarily periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     carbohyd
    -0.80
     transition
    -0.74
     integ
    -0.73
     complementary
    -0.72
     isot
    -0.72
     heavily
    -0.70
     interpreter
    -0.70
     extensively
    -0.70
     proport
    -0.69
     advoc
    -0.69
    POSITIVE LOGITS
     Nope
    1.39
     Instead
    1.31
     Surely
    1.30
     Or
    1.24
     Maybe
    1.22
     Alas
    1.21
     Wouldn
    1.20
     Perhaps
    1.16
     Sure
    1.15
     Somehow
    1.15
    Act Density 0.491%

    No Known Activations