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

    Neuronpedia

    INDEX
    Explanations

    phrases related to historical policies or practices

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     impelled
    -0.70
     Shakspeare
    -0.69
     endeavouring
    -0.67
     McLaugh
    -0.66
     Daven
    -0.63
     assailed
    -0.63
     endeavoured
    -0.60
     vainly
    -0.59
     exagger
    -0.59
     gaily
    -0.59
    POSITIVE LOGITS
     reasons
    0.99
    reasons
    0.88
    madeus
    0.80
     REASONS
    0.78
     Reasons
    0.77
    Reasons
    0.75
     purposes
    0.73
     raisons
    0.72
     affez
    0.72
     divertimento
    0.72
    Act Density 0.229%

    No Known Activations