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

    Neuronpedia

    INDEX
    Explanations

    statistical data related to political figures' rankings and percentages

    oai_token-act-pair · gpt-3.5-turbo

    percentage representations of support or votes for various political figures or parties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ
    -0.68
     "$:/
    -0.65
    ĨĴ
    -0.60
     NEVER
    -0.57
    £ı
    -0.56
    aroo
    -0.54
    ĸļ
    -0.51
     subsequ
    -0.51
    wcsstore
    -0.51
     Transcript
    -0.50
    POSITIVE LOGITS
     apiece
    1.44
     respectively
    1.24
    %.
    1.12
    +.
    0.96
    .
    0.92
    %;
    0.91
    .;
    0.89
    %,
    0.84
    ;
    0.83
    .).
    0.83
    Act Density 0.308%

    No Known Activations