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

    Neuronpedia

    INDEX
    Explanations

    timestamps and dates

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    nell
    -0.68
     thriving
    -0.63
    alties
    -0.60
     flourishing
    -0.58
     gull
    -0.58
     lining
    -0.57
    amorph
    -0.56
     thri
    -0.56
     Towns
    -0.56
    æ©
    -0.56
    POSITIVE LOGITS
     disclaimer
    1.09
     summarize
    1.08
     briefly
    1.02
     recap
    1.01
     spoiler
    0.96
     reiterate
    0.96
    claimer
    0.95
     spoilers
    0.94
     summar
    0.94
     caveats
    0.92
    Act Density 2.033%

    No Known Activations