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

    Neuronpedia

    INDEX
    Explanations

    references to asylum seekers

    oai_token-act-pair · gpt-3.5-turbo

    references to asylum seekers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hobby
    -0.72
     Kers
    -0.70
     snipp
    -0.67
     Tire
    -0.65
    Eat
    -0.64
     Nicotine
    -0.64
     antioxid
    -0.63
     Toast
    -0.63
     smoker
    -0.62
     Tet
    -0.61
    POSITIVE LOGITS
     seeker
    1.54
     seekers
    1.50
    ylum
    1.13
     asylum
    0.97
     refugee
    0.95
     Refugees
    0.94
     clearance
    0.91
     resettlement
    0.90
     detain
    0.89
     refugees
    0.86
    Act Density 0.027%

    No Known Activations