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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political parties and government control

    oai_token-act-pair · gpt-3.5-turbo

    negative political affiliations or control dynamics between political parties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reservoirs
    -0.78
     scratch
    -0.73
     balls
    -0.73
     redund
    -0.71
     thumbnail
    -0.71
     clocks
    -0.71
     twenties
    -0.69
     dusk
    -0.69
     leap
    -0.69
     Brus
    -0.68
    POSITIVE LOGITS
    dominated
    1.94
    controlled
    1.70
    aligned
    1.61
    leaning
    1.53
    affiliated
    1.52
    friendly
    1.48
    majority
    1.47
    owned
    1.46
    themed
    1.45
    inspired
    1.42
    Act Density 0.061%

    No Known Activations