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

    Neuronpedia

    INDEX
    Explanations

    references to academic researchers and their work

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    BuyableInstoreAndOnline
    -0.73
     Rapids
    -0.66
     Leilan
    -0.62
     Tribal
    -0.60
    swing
    -0.60
    stick
    -0.59
    atra
    -0.59
     Maiden
    -0.59
    boats
    -0.59
     Pradesh
    -0.58
    POSITIVE LOGITS
    Researchers
    0.90
     researcher
    0.89
     studying
    0.89
     Researchers
    0.88
    hran
    0.86
    hips
    0.83
     researching
    0.83
     scientist
    0.82
    sonian
    0.81
     researchers
    0.80
    Act Density 0.033%

    No Known Activations