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

    Neuronpedia

    INDEX
    Explanations

    statistics or facts about large groups of people, particularly in a global context

    oai_token-act-pair · gpt-3.5-turbo

    references to the number of people affected by various situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odox
    -0.78
     Monkey
    -0.69
    SourceFile
    -0.69
     Dispatch
    -0.66
     Ratt
    -0.65
     Handler
    -0.63
     Franch
    -0.63
     Inquis
    -0.62
     Silence
    -0.61
     Courier
    -0.60
    POSITIVE LOGITS
     worldwide
    1.11
     nationwide
    0.93
     annually
    0.89
     crammed
    0.89
     surveyed
    0.80
     apiece
    0.79
     marched
    0.79
     polled
    0.76
    illion
    0.76
     globally
    0.76
    Act Density 0.185%

    No Known Activations