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

    Neuronpedia

    INDEX
    Explanations

    phrases related to social, political, or cultural commentary

    oai_token-act-pair · gpt-3.5-turbo

    elements of feminism and social critique

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     LCS
    -0.64
     Lands
    -0.62
     GEAR
    -0.59
     Lans
    -0.58
     Webs
    -0.55
    draft
    -0.54
     RHP
    -0.54
     Sites
    -0.54
     Yellowstone
    -0.54
    emonium
    -0.53
    POSITIVE LOGITS
     jealous
    0.64
     remorse
    0.62
    ernel
    0.59
     envy
    0.59
     regret
    0.58
     negatively
    0.58
     urge
    0.57
     dissatisfied
    0.57
     mistrust
    0.57
     believing
    0.57
    Act Density 1.632%

    No Known Activations