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

    Neuronpedia

    INDEX
    Explanations

    terms related to historical and political events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     ability
    -0.81
     undet
    -0.77
     coral
    -0.75
     bloc
    -0.74
     lifes
    -0.74
     inclusion
    -0.74
     carriage
    -0.74
     hatch
    -0.73
     payroll
    -0.73
     covenant
    -0.73
    POSITIVE LOGITS
    Advertisement
    1.91
    But
    1.69
    Instead
    1.64
    Perhaps
    1.61
    Yet
    1.61
    That
    1.61
    Fortunately
    1.61
    Then
    1.61
    When
    1.60
    Unfortunately
    1.60
    Act Density 1.310%

    No Known Activations