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

    Neuronpedia

    INDEX
    Explanations

    words related to competition or being considered for a specific position or title

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    imar
    -0.83
    arching
    -0.73
    engineering
    -0.69
    Ku
    -0.69
     Spa
    -0.66
    romy
    -0.66
     Gazette
    -0.66
    mut
    -0.65
    uras
    -0.63
    ported
    -0.63
    POSITIVE LOGITS
     contender
    1.42
     contenders
    1.32
     frontrunner
    1.06
     competitor
    1.01
     contestant
    0.98
     challengers
    0.92
     finalists
    0.88
     challenger
    0.88
     competitors
    0.86
     contestants
    0.86
    Act Density 0.012%

    No Known Activations