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

    Neuronpedia

    INDEX
    Explanations

    cities and countries

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations, nations, and political or social organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     provisional
    -0.63
    shown
    -0.62
     recomm
    -0.62
    eatures
    -0.61
     newcom
    -0.58
     watchdog
    -0.57
    language
    -0.57
    atile
    -0.57
    continue
    -0.56
     resource
    -0.55
    POSITIVE LOGITS
     or
    1.26
     anymore
    1.08
     circa
    0.97
     etc
    0.87
    .?
    0.87
    ombies
    0.83
    ?
    0.82
    ????
    0.82
     nor
    0.78
     :(
    0.75
    Act Density 0.550%

    No Known Activations