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

    Neuronpedia

    INDEX
    Explanations

    sentences about an action or event taking place in the future

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    76561
    -0.70
     imagination
    -0.69
    conn
    -0.67
    rehens
    -0.67
    itability
    -0.66
     Oops
    -0.65
    usc
    -0.64
    rawdownloadcloneembedreportprint
    -0.63
    intent
    -0.63
     innocence
    -0.61
    POSITIVE LOGITS
     replaced
    1.02
     phased
    1.00
     unveiled
    0.97
     judged
    0.93
     evaluated
    0.93
     showcased
    0.91
     able
    0.91
     featured
    0.90
     released
    0.89
     rewarded
    0.87
    Act Density 0.126%

    No Known Activations