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

    Neuronpedia

    INDEX
    Explanations

    terms associated with change and improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rings
    -0.68
    trak
    -0.66
    ucci
    -0.65
     sounded
    -0.60
     prevailed
    -0.60
     Enabled
    -0.59
     Lauder
    -0.58
    rouse
    -0.58
     shines
    -0.58
     beck
    -0.58
    POSITIVE LOGITS
    DonaldTrump
    0.73
     peoples
    0.69
    etheus
    0.68
    Reviewer
    0.67
    iability
    0.67
     mankind
    0.64
     havoc
    0.64
     comprehension
    0.63
     susceptibility
    0.62
     productivity
    0.61
    Act Density 0.141%

    No Known Activations