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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific laws or regulations

    oai_token-act-pair · gpt-3.5-turbo

    references to laws and regulations affecting societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Keys
    -0.53
     Disclosure
    -0.51
     awoke
    -0.51
    SW
    -0.51
     Charm
    -0.50
     wasn
    -0.49
     Stim
    -0.49
     Ange
    -0.48
     Rh
    -0.48
     Britt
    -0.48
    POSITIVE LOGITS
     indistinguishable
    0.68
     descendants
    0.65
     apiece
    0.64
     yearly
    0.63
     theirs
    0.62
    kefeller
    0.60
     toget
    0.59
    athered
    0.58
     nowadays
    0.57
    quartered
    0.56
    Act Density 1.586%

    No Known Activations