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

    Neuronpedia

    INDEX
    Explanations

    physical locations and names of places

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    yip
    -1.01
     centrif
    -0.99
     Shutterstock
    -0.99
     dime
    -0.97
     scales
    -0.92
     tongue
    -0.91
     litter
    -0.90
     elevation
    -0.89
     stool
    -0.87
     proxies
    -0.87
    POSITIVE LOGITS
    enment
    1.19
    ale
    1.13
    rences
    1.10
    çĶŁ
    1.09
    lement
    1.08
    aton
    1.06
    assing
    1.04
    stellar
    1.04
    ãĤ¼ãĤ¦ãĤ¹
    1.03
    rative
    1.02
    Act Density 2.152%

    No Known Activations