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

    Neuronpedia

    INDEX
    Explanations

    names of people and places

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Clover
    -0.67
     endowed
    -0.65
     sterling
    -0.60
     Calder
    -0.55
     Grimes
    -0.55
     silent
    -0.55
     pim
    -0.54
     glass
    -0.54
     Kessler
    -0.53
     maintaining
    -0.53
    POSITIVE LOGITS
    pta
    0.87
    adic
    0.81
    atoon
    0.80
    oku
    0.78
    anka
    0.77
    oslav
    0.77
    hom
    0.76
    inx
    0.75
    iman
    0.73
    atchewan
    0.72
    Act Density 0.058%

    No Known Activations