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

    Neuronpedia

    INDEX
    Explanations

    information related to educational backgrounds and professional experiences, particularly in the fields of leadership, creative writing, and education

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    oked
    -0.92
    metadata
    -0.91
     Horde
    -0.84
     unreasonable
    -0.84
     hypoc
    -0.83
    comfort
    -0.81
     clam
    -0.81
    engers
    -0.78
    zers
    -0.78
    bugs
    -0.78
    POSITIVE LOGITS
     undergraduate
    1.70
     graduate
    1.57
     Degree
    1.53
    ploma
    1.50
     doctoral
    1.50
     undergrad
    1.47
     dissertation
    1.45
    graduate
    1.43
     Graduate
    1.38
     diploma
    1.36
    Act Density 4.242%

    No Known Activations