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

    Neuronpedia

    INDEX
    Explanations

    politicians' last names

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of politicians and public figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lehem
    -0.88
     Corpus
    -0.75
    Copyright
    -0.68
    olulu
    -0.68
    Redd
    -0.64
    awks
    -0.64
     Tasman
    -0.64
    ãĥŁ
    -0.63
     Artemis
    -0.63
     neutron
    -0.62
    POSITIVE LOGITS
     himself
    1.22
    's
    0.97
     personally
    0.94
     Himself
    0.87
    ism
    0.85
     swore
    0.82
     aides
    0.79
    Care
    0.77
    isms
    0.77
     lied
    0.77
    Act Density 0.174%

    No Known Activations