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

    Neuronpedia

    INDEX
    Explanations

    references to significant geopolitical events and issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.43
    1:0.01
    2:0.12
    3:0.10
    4:0.02
    5:0.07
    6:0.02
    7:0.05
    8:0.06
    9:0.02
    10:0.03
    11:0.02
    Negative Logits
    Wisconsin
    -2.47
    Origin
    -2.41
    Denver
    -2.33
    Toronto
    -2.31
    Seattle
    -2.23
    Mexico
    -2.17
    Chicago
    -2.16
    alore
    -2.11
    eus
    -2.09
    Michigan
    -2.06
    POSITIVE LOGITS
     population
    2.53
     Unemployment
    2.51
    population
    2.26
     inhabitants
    2.13
     reun
    2.12
     harbor
    2.09
     unemployment
    2.05
     thriving
    1.98
     democratically
    1.96
     Communism
    1.95
    Act Density 1.256%

    No Known Activations