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

    Neuronpedia

    INDEX
    Explanations

    the term "Tea Party"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Tea Party movement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ities
    -0.83
    istically
    -0.78
    theless
    -0.76
    osure
    -0.75
    rf
    -0.70
    phis
    -0.69
    ospace
    -0.69
    cy
    -0.68
    itals
    -0.68
    ials
    -0.68
    POSITIVE LOGITS
     leaf
    0.91
     Leaf
    0.90
     Leaves
    0.89
     towels
    0.88
     kettle
    0.87
     leaves
    0.84
     towel
    0.81
     drinkers
    0.79
    pling
    0.79
    pler
    0.79
    Act Density 0.038%

    No Known Activations