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

    Neuronpedia

    INDEX
    Explanations

    descriptions related to news events or incidents involving individuals

    oai_token-act-pair · gpt-3.5-turbo

    the presence of subjects and their descriptions in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cean
    -0.68
    scl
    -0.62
    orts
    -0.62
     Versus
    -0.61
    olate
    -0.60
    kefeller
    -0.60
    "]=>
    -0.59
    psc
    -0.59
    eties
    -0.58
     Dragonbound
    -0.58
    POSITIVE LOGITS
     identified
    1.17
     whom
    1.15
    whose
    1.13
     whose
    1.13
     who
    1.12
    who
    1.11
     surn
    1.03
     believed
    1.02
     named
    1.00
     nicknamed
    0.97
    Act Density 0.145%

    No Known Activations