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

    Neuronpedia

    INDEX
    Explanations

    words related to specific nationalities

    oai_token-act-pair · gpt-3.5-turbo

    references to demographic groups and their sentiments or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    advertisement
    -0.73
     Subtle
    -0.67
    ĸļ
    -0.66
    LOD
    -0.64
    Dur
    -0.64
    Impro
    -0.64
     Engineers
    -0.64
    forcement
    -0.63
     CRC
    -0.62
    Prov
    -0.61
    POSITIVE LOGITS
     resent
    1.45
     distrust
    1.38
     sympath
    1.35
     despise
    1.32
     mistrust
    1.31
     disapprove
    1.29
     dislike
    1.25
     oppose
    1.25
     fear
    1.22
     abhor
    1.21
    Act Density 0.315%

    No Known Activations