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

    Neuronpedia

    INDEX
    Explanations

    words related to political discourse

    oai_token-act-pair · gpt-3.5-turbo

    references to people's relationships and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥ³
    -1.05
    ĸļ
    -0.88
    iHUD
    -0.86
    utenberg
    -0.86
    ãĥ¯ãĥ³
    -0.84
    paralleled
    -0.80
    foreseen
    -0.76
    rium
    -0.76
    viation
    -0.74
    ledged
    -0.74
    POSITIVE LOGITS
     they
    1.08
     rapists
    0.99
     politicians
    0.98
     dictators
    0.98
     husbands
    0.97
     THEY
    0.97
     criminals
    0.97
    they
    0.96
     majorities
    0.92
     governments
    0.91
    Act Density 0.402%

    No Known Activations