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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political figures and office positions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    arrow
    -0.71
    complex
    -0.67
    iw
    -0.66
    ighed
    -0.66
    iven
    -0.65
    polit
    -0.63
    orry
    -0.63
    acid
    -0.63
    rather
    -0.62
    gru
    -0.62
    POSITIVE LOGITS
     victory
    0.98
     nomination
    0.93
     citizenship
    0.92
     immortality
    0.91
     presidency
    0.90
     supremacy
    0.90
     prizes
    0.89
     fame
    0.87
     entry
    0.87
     redemption
    0.87
    Act Density 1.405%

    No Known Activations