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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal or political controversies

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ģĸ
    -0.71
    rontal
    -0.67
    vision
    -0.66
    ãĥ¼ãĤ¯
    -0.66
    enes
    -0.65
    alus
    -0.64
    ayan
    -0.64
    anni
    -0.63
    aukee
    -0.63
    ogie
    -0.62
    POSITIVE LOGITS
     news
    0.65
     misfortune
    0.61
     impending
    0.59
     irregularities
    0.58
     announcing
    0.58
     Newtown
    0.56
    bryce
    0.55
    availability
    0.55
     unfamiliar
    0.55
     arrival
    0.55
    Act Density 9.670%

    No Known Activations