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

    Neuronpedia

    INDEX
    Explanations

    texts related to establishing or creating something, like institutions, governance mechanisms, territory, or new colonies

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ã
    -0.68
    eware
    -0.67
    Boy
    -0.66
    ï¸
    -0.66
    QL
    -0.64
    hop
    -0.63
    ÃŃa
    -0.63
    ffield
    -0.63
    Bey
    -0.63
    phe
    -0.62
    POSITIVE LOGITS
     Lauder
    0.86
    lishes
    0.83
     relationships
    0.76
     partnerships
    0.75
     anew
    0.74
     friendships
    0.73
     establishes
    0.72
     alliances
    0.72
    eers
    0.72
    iates
    0.71
    Act Density 9.129%

    No Known Activations