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

    Neuronpedia

    INDEX
    Explanations

    negative opinions or critiques about political figures or institutions

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing criticism or negative views regarding political figures and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    earchers
    -0.80
    ngth
    -0.79
    aunder
    -0.78
    nings
    -0.75
    cue
    -0.72
     teasp
    -0.72
    cano
    -0.71
    case
    -0.71
    ograp
    -0.70
    pection
    -0.69
    POSITIVE LOGITS
     capitalism
    0.97
     homosexuality
    0.96
     politicians
    0.90
     liberalism
    0.89
     Islam
    0.84
     outsiders
    0.82
     foreigners
    0.82
     incumb
    0.81
     gays
    0.81
     homosexuals
    0.80
    Act Density 0.192%

    No Known Activations