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

    Neuronpedia

    INDEX
    Explanations

    phrases related to community revitalization and social issues

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    rique
    -0.85
     fronts
    -0.74
    rers
    -0.66
    hoe
    -0.66
    onde
    -0.62
    ode
    -0.62
    tyard
    -0.61
    ursday
    -0.61
    oder
    -0.61
    ¬¼
    -0.60
    POSITIVE LOGITS
     namely
    0.82
     viz
    0.80
    whether
    0.78
     THEN
    0.77
    BUT
    0.68
    excluding
    0.67
    etc
    0.64
     whether
    0.63
    kl
    0.62
     etc
    0.62
    Act Density 21.486%

    No Known Activations