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

    Neuronpedia

    INDEX
    Explanations

    references to ideological biases and political disagreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    688
    -0.20
     conservative
    -0.18
     conserv
    -0.18
     homophobic
    -0.18
     conservatives
    -0.17
     conservatism
    -0.17
     Tory
    -0.17
     patriarch
    -0.16
    Ñħи
    -0.15
     neoliberal
    -0.15
    POSITIVE LOGITS
     leftist
    0.26
    -left
    0.25
     Left
    0.23
    /left
    0.21
     left
    0.21
     PC
    0.20
     Marxist
    0.19
    Left
    0.19
     LEFT
    0.19
     Soros
    0.19
    Act Density 0.412%

    No Known Activations