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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences where someone is being quoted

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    à¼
    -0.92
    Login
    -0.81
    atown
    -0.79
    anuts
    -0.76
    200000
    -0.73
    ById
    -0.73
    xx
    -0.72
    endars
    -0.72
    venth
    -0.72
    Offline
    -0.71
    POSITIVE LOGITS
     Jennifer
    1.21
     spokesman
    1.20
     Jonathan
    1.18
     Kevin
    1.17
     David
    1.16
     Karen
    1.16
     Linda
    1.16
     Julie
    1.15
     spokeswoman
    1.15
     Kathleen
    1.15
    Act Density 0.067%

    No Known Activations