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

    Neuronpedia

    INDEX
    Explanations

    words related to information lookup or facts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     levers
    -0.74
    ĸļ
    -0.72
     numbering
    -0.71
     graph
    -0.70
     proxies
    -0.69
     Citation
    -0.64
     iod
    -0.63
     THR
    -0.61
     paralle
    -0.61
     datas
    -0.60
    POSITIVE LOGITS
    zee
    0.89
    uously
    0.80
    agic
    0.75
    ufact
    0.75
    estation
    0.73
    ose
    0.72
    andise
    0.70
    aunts
    0.70
    oppers
    0.70
    ishes
    0.70
    Act Density 0.066%

    No Known Activations