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

    Neuronpedia

    INDEX
    Explanations

    phrases related to research studies and their findings

    oai_token-act-pair · gpt-3.5-turbo

    mentions of researchers or research activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Maiden
    -0.67
     Passage
    -0.63
    BuyableInstoreAndOnline
    -0.60
     Pradesh
    -0.60
     Rapids
    -0.58
    Enough
    -0.58
     Judgment
    -0.58
    lite
    -0.57
     Flames
    -0.57
    stick
    -0.56
    POSITIVE LOGITS
     Researchers
    0.88
    Researchers
    0.87
    hran
    0.85
    hips
    0.84
    paces
    0.83
     studying
    0.81
     researcher
    0.80
     researching
    0.79
    hip
    0.78
    sonian
    0.78
    Act Density 0.029%

    No Known Activations