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

    Neuronpedia

    INDEX
    Explanations

    mentions of people or events in news articles

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     polyg
    -0.78
     showers
    -0.70
     lapse
    -0.64
     Objects
    -0.64
     detail
    -0.61
     consum
    -0.61
     Redd
    -0.61
     Templ
    -0.59
     brig
    -0.58
     contrace
    -0.58
    POSITIVE LOGITS
    til
    1.30
    Cause
    1.06
    cause
    1.03
    Mech
    0.98
    tis
    0.93
    ths
    0.85
    arak
    0.85
    Interstitial
    0.83
    atri
    0.83
    cue
    0.83
    Act Density 0.041%

    No Known Activations