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

    Neuronpedia

    INDEX
    Explanations

    a wide variety of topics, issues, and details in extensive texts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    henko
    -0.81
    fter
    -0.78
    ovember
    -0.77
    vest
    -0.77
    rade
    -0.72
    uca
    -0.71
    hao
    -0.70
    few
    -0.69
    roth
    -0.68
    iva
    -0.68
    POSITIVE LOGITS
     sorts
    1.25
     different
    0.98
     ways
    0.98
     possibilities
    0.98
     facets
    0.96
     assorted
    0.94
     occasions
    0.94
    things
    0.93
     varying
    0.91
     imaginable
    0.91
    Act Density 1.766%

    No Known Activations