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

    Neuronpedia

    INDEX
    Explanations

    Twitter usernames

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     habitat
    -0.76
     upkeep
    -0.74
     commissions
    -0.71
     cons
    -0.71
     residency
    -0.69
     puberty
    -0.69
     charm
    -0.67
     starved
    -0.67
     concerts
    -0.67
     accredited
    -0.65
    POSITIVE LOGITS
    Twe
    0.99
    Wh
    0.97
    Comments
    0.94
    Loading
    0.93
    [/
    0.92
    RIP
    0.90
    Tweet
    0.88
    20439
    0.87
    Twitter
    0.85
    WH
    0.84
    Act Density 12.496%

    No Known Activations