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

    Neuronpedia

    INDEX
    Explanations

    names of people or characters

    oai_token-act-pair · gpt-3.5-turbo

    names and numerical data, particularly related to reports or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    à©
    -0.53
    umbn
    -0.47
    é¾į
    -0.47
    /
    -0.46
    albeit
    -0.44
    "},"
    -0.43
    æ©Ł
    -0.42
    à¨
    -0.42
     namely
    -0.41
    absolutely
    -0.41
    POSITIVE LOGITS
    ,.
    1.13
    ,
    1.03
    .,
    1.01
    ,...
    0.96
    ?,
    0.94
    ,,
    0.89
    .
    0.84
    !,
    0.82
    ,,,,
    0.81
    .).
    0.80
    Act Density 0.924%

    No Known Activations