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

    Neuronpedia

    INDEX
    Explanations

    phrases related to playing and interacting with objects or people

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    hra
    -0.64
    fighter
    -0.62
    omsky
    -0.58
    nery
    -0.57
    FY
    -0.55
    mite
    -0.54
    anski
    -0.54
    UME
    -0.53
    mart
    -0.53
    Ö¼
    -0.53
    POSITIVE LOGITS
     dolls
    0.80
     impunity
    0.73
    draw
    0.71
    è¦ļéĨĴ
    0.68
    stood
    0.67
    standing
    0.66
     regard
    0.66
     dignity
    0.65
     regards
    0.64
     toys
    0.64
    Act Density 11.253%

    No Known Activations