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

    Neuronpedia

    INDEX
    Explanations

    key terms and phrases related to beliefs, values, and representations in a societal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Coronavirus
    -0.18
     coronavirus
    -0.18
     covid
    -0.17
     COVID
    -0.16
     Brexit
    -0.16
    202
    -0.16
     ðŁĶ
    -0.16
    COVID
    -0.15
     Covid
    -0.15
     ì½Ķë¡ľëĤĺ
    -0.15
    POSITIVE LOGITS
     gay
    0.28
     heterosexual
    0.28
     gays
    0.26
     homosexuals
    0.25
     homophobic
    0.24
     Gay
    0.24
     homosexual
    0.24
     homosexuality
    0.24
     intolerance
    0.23
     heter
    0.23
    Act Density 0.045%

    No Known Activations