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

    Neuronpedia

    INDEX
    Explanations

    terms related to progressive politics or movements

    oai_token-act-pair · gpt-3.5-turbo

    repeated patterns or structures of text that indicate a specific classification or category

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sworth
    -0.81
    ordon
    -0.80
    gins
    -0.77
    iceps
    -0.77
    obyl
    -0.75
    abba
    -0.74
    istically
    -0.73
    acca
    -0.72
    fleet
    -0.70
    lessly
    -0.69
    POSITIVE LOGITS
    gressive
    0.88
     taxation
    0.87
     ideals
    0.86
     thinkers
    0.83
     stances
    0.81
     minded
    0.78
     activist
    0.77
     ideology
    0.77
     progressive
    0.73
     activists
    0.73
    Act Density 0.031%

    No Known Activations