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

    Neuronpedia

    INDEX
    Explanations

    timestamps and user actions in discussions or conversations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     prophets
    -0.75
     metic
    -0.74
     drib
    -0.70
     mug
    -0.69
     elbow
    -0.69
     charm
    -0.68
     brewed
    -0.68
     playbook
    -0.67
     chanted
    -0.66
    ô
    -0.66
    POSITIVE LOGITS
    UTC
    1.14
    Hello
    0.87
    ajor
    0.87
    Awesome
    0.83
    Status
    0.82
    Excellent
    0.80
    reply
    0.80
    Congratulations
    0.79
    Rate
    0.78
    Dear
    0.78
    Act Density 11.979%

    No Known Activations