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

    Neuronpedia

    INDEX
    Explanations

    phrases related to future plans or projects

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    Reporting
    -0.80
    ombat
    -0.78
    ordinary
    -0.72
     Mub
    -0.71
     observes
    -0.66
     Parables
    -0.64
    arov
    -0.63
    phys
    -0.62
    vers
    -0.62
    ér
    -0.62
    POSITIVE LOGITS
     impending
    1.18
     imminent
    1.14
     doom
    1.00
     future
    0.99
     someday
    0.96
     upcoming
    0.93
     prospects
    0.87
     renewal
    0.86
     tomorrow
    0.86
     looming
    0.82
    Act Density 8.271%

    No Known Activations