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

    Neuronpedia

    INDEX
    Explanations

    comments related to immigration and public policy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     herewith
    -0.90
     skall
    -0.88
     marvelous
    -0.88
     endeav
    -0.85
     endeavored
    -0.84
     Utilizing
    -0.82
     فريبيس
    -0.82
     etiology
    -0.82
     utilize
    -0.82
     parameterized
    -0.80
    POSITIVE LOGITS
     bosses
    0.91
     Mr
    0.66
    Mr
    0.63
     criticised
    0.63
     boss
    0.61
     Nato
    0.61
     chiefs
    0.58
     fears
    0.57
     feared
    0.55
     £
    0.55
    Act Density 0.431%

    No Known Activations