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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to politics, specific people, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to governmental or political processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .).
    -0.70
    !".
    -0.66
    ]."
    -0.66
    ".
    -0.62
    ?".
    -0.59
    }.
    -0.58
    ]).
    -0.58
    .</
    -0.57
    )).
    -0.56
    ''.
    -0.54
    POSITIVE LOGITS
    odore
    0.56
    ngth
    0.50
    romeda
    0.48
    swers
    0.47
    ividual
    0.47
    reenshots
    0.46
    imaru
    0.45
     divided
    0.44
     Aberdeen
    0.44
    arcity
    0.44
    Act Density 2.640%

    No Known Activations