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

    Neuronpedia

    INDEX
    Explanations

    information about recent events or developments

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    arta
    -0.85
     cylinders
    -0.68
     Tycoon
    -0.66
     Borders
    -0.66
    ooters
    -0.65
    ooter
    -0.62
    arily
    -0.61
    onto
    -0.60
    atically
    -0.60
     Higgins
    -0.59
    POSITIVE LOGITS
     plenty
    0.96
     murm
    0.86
     tremendous
    0.79
     uproar
    0.76
     whispers
    0.75
     considerable
    0.75
     conflicting
    0.74
     renewed
    0.74
     noticeable
    0.73
     enough
    0.73
    Act Density 0.030%

    No Known Activations