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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social and political issues, economic inequality, and community welfare

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    auga
    -0.62
    uador
    -0.59
    arter
    -0.57
    ande
    -0.55
    thood
    -0.55
    zie
    -0.54
    nikov
    -0.53
    andum
    -0.53
    ritz
    -0.53
    gat
    -0.52
    POSITIVE LOGITS
    pires
    0.77
     turns
    0.65
     translates
    0.61
    ifies
    0.57
     happens
    0.56
     turned
    0.54
     itself
    0.54
    ãĤ©
    0.53
     describes
    0.53
    ¢
    0.53
    Act Density 12.495%

    No Known Activations