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

    Neuronpedia

    INDEX
    Explanations

    phrases related to time and progression

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    insky
    -0.63
     Dating
    -0.62
     Limits
    -0.62
    global
    -0.61
    Center
    -0.61
    STER
    -0.61
     outdoors
    -0.59
    outside
    -0.59
    rored
    -0.59
     Across
    -0.59
    POSITIVE LOGITS
     unsc
    0.86
     refreshed
    0.82
     disgrace
    0.82
     handsome
    0.77
     sooner
    0.77
     quicker
    0.76
     intact
    0.76
     regrets
    0.75
     wiser
    0.75
    morrow
    0.75
    Act Density 0.274%

    No Known Activations