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

    Neuronpedia

    INDEX
    Explanations

    political entities and events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    rett
    -0.73
    inet
    -0.72
    yt
    -0.69
    reys
    -0.69
    nell
    -0.67
    lished
    -0.66
    kson
    -0.65
    obin
    -0.65
    none
    -0.65
    lled
    -0.65
    POSITIVE LOGITS
     Republic
    0.93
     Association
    0.93
     Liberation
    0.92
     Assembly
    0.91
     Organization
    0.86
     Directorate
    0.85
     Choice
    0.85
     Militia
    0.84
     Council
    0.83
     Bank
    0.83
    Act Density 0.048%

    No Known Activations