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

    Neuronpedia

    INDEX
    Explanations

    statistics and numerical information

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    NetMessage
    -0.94
     orient
    -0.65
     Flavoring
    -0.65
    assies
    -0.64
    ovie
    -0.64
     Belg
    -0.64
    Interstitial
    -0.63
    heny
    -0.63
    ipher
    -0.63
     prolet
    -0.62
    POSITIVE LOGITS
     estimates
    1.00
     averages
    0.94
     excludes
    0.89
     estimate
    0.88
     exceeded
    0.87
     totaled
    0.87
     tallied
    0.86
     exceeds
    0.86
     varies
    0.86
     extrap
    0.84
    Act Density 0.075%

    No Known Activations