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

    Neuronpedia

    INDEX
    Explanations

    connections among social, political, and economic themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.04
    2:0.03
    3:0.04
    4:0.17
    5:0.02
    6:0.03
    7:0.44
    8:0.02
    9:0.04
    10:0.03
    11:0.07
    Negative Logits
     SOC
    -3.51
     Social
    -3.14
     Soc
    -2.97
    Social
    -2.95
     SJ
    -2.86
     socialists
    -2.84
     Socialism
    -2.75
     Synd
    -2.73
    "]=>
    -2.71
     Syd
    -2.68
    POSITIVE LOGITS
     Boll
    3.00
    oglu
    2.97
     Alonso
    2.90
    uba
    2.54
     Boyle
    2.51
     Burke
    2.50
    alez
    2.44
    uliffe
    2.41
    uterte
    2.40
     Magnum
    2.40
    Act Density 0.025%

    No Known Activations