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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political activities or events

    oai_token-act-pair · gpt-3.5-turbo

    references to political events and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ratulations
    -0.58
    !",
    -0.57
    /,
    -0.53
    ",
    -0.51
    ortun
    -0.50
     Which
    -0.49
    POSE
    -0.49
    ',
    -0.47
    %,
    -0.47
    aque
    -0.47
    POSITIVE LOGITS
    .�
    0.86
    .''.
    0.86
     but
    0.85
    .''
    0.76
    .ãĢį
    0.75
    }.
    0.74
     albeit
    0.73
     }}
    0.72
    but
    0.72
    .</
    0.71
    Act Density 0.997%

    No Known Activations