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

    Neuronpedia

    INDEX
    Explanations

    phrases related to global influence and status

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ardless
    -0.75
    hift
    -0.67
    unciation
    -0.64
    omething
    -0.61
    displayText
    -0.61
    ertation
    -0.60
    ench
    -0.60
    èª
    -0.60
    osis
    -0.60
    ersion
    -0.59
    POSITIVE LOGITS
    's
    1.05
    ´
    1.00
     busiest
    0.95
    \'
    0.93
    ÃŃs
    0.93
     deadliest
    0.84
     tallest
    0.83
     oldest
    0.83
     wealthiest
    0.82
     brightest
    0.82
    Act Density 0.088%

    No Known Activations