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

    Neuronpedia

    INDEX
    Explanations

    words related to rulings in political contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to governing bodies or political parties in a ruling context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Granger
    -0.85
    chie
    -0.72
    aged
    -0.71
     Gard
    -0.69
    appy
    -0.66
     Sins
    -0.66
     CFL
    -0.65
     Bow
    -0.64
     Wyatt
    -0.63
     Webster
    -0.62
    POSITIVE LOGITS
     ruling
    1.16
     rulings
    0.88
    uling
    0.88
     rul
    0.88
     ruled
    0.86
     dict
    0.84
     prevail
    0.76
    dict
    0.76
    maker
    0.76
    eering
    0.75
    Act Density 0.009%

    No Known Activations