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

    Neuronpedia

    INDEX
    Explanations

    mentions of the future

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    lee
    -0.85
    nai
    -0.76
    quet
    -0.76
    ideshow
    -0.75
    die
    -0.74
    tha
    -0.74
    lez
    -0.71
    edin
    -0.71
    ateurs
    -0.69
    cano
    -0.68
    POSITIVE LOGITS
     generations
    1.06
     prospects
    0.97
     outlook
    0.95
     trajectory
    0.91
     horizon
    0.91
     occupant
    0.87
    izons
    0.83
     Directions
    0.82
     traject
    0.81
     selves
    0.80
    Act Density 0.048%

    No Known Activations