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

    Neuronpedia

    INDEX
    Explanations

    references to the "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
    theless
    -1.06
    ities
    -0.81
    aird
    -0.79
    raints
    -0.78
    phis
    -0.76
    alities
    -0.74
    ionic
    -0.74
    animous
    -0.74
    */(
    -0.73
    nesota
    -0.72
    POSITIVE LOGITS
     Tea
    1.04
     Leaf
    0.95
    Tea
    0.91
    zza
    0.80
     Party
    0.80
    ptives
    0.79
     tea
    0.78
     towels
    0.75
    enza
    0.73
     Garden
    0.69
    Act Density 0.007%

    No Known Activations