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

    Neuronpedia

    INDEX
    Explanations

    mention of political campaigns and election-related activities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ighed
    -0.75
    alam
    -0.71
    isson
    -0.63
     Wond
    -0.62
    âĨij
    -0.62
    ":["
    -0.60
     Hubble
    -0.59
    omical
    -0.59
    atican
    -0.59
     Uriel
    -0.59
    POSITIVE LOGITS
     mate
    0.87
     campaigns
    0.85
    clinton
    0.85
    escape
    0.82
    running
    0.82
     candidacy
    0.79
    ulators
    0.79
    agate
    0.77
    runner
    0.77
     candidates
    0.76
    Act Density 0.037%

    No Known Activations