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

    Neuronpedia

    INDEX
    Explanations

    government-related terms like titles, positions, and institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to governmental or state-related entities and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ï¸ı
    -0.87
    Frames
    -0.80
    ï¸
    -0.71
    Transform
    -0.65
    pload
    -0.63
    ersen
    -0.62
    rawdownloadcloneembedreportprint
    -0.62
    Shell
    -0.62
    axis
    -0.62
    ipel
    -0.62
    POSITIVE LOGITS
    aucuses
    0.81
     trooper
    0.74
    sylvania
    0.72
    hyde
    0.71
     troopers
    0.70
     reserve
    0.65
     Marshal
    0.62
    itol
    0.61
     Watkins
    0.61
     legislatures
    0.61
    Act Density 0.190%

    No Known Activations