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

    Neuronpedia

    INDEX
    Explanations

    subjects related to social and political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.17
    1:0.04
    2:0.01
    3:0.09
    4:0.24
    5:0.18
    6:0.03
    7:0.01
    8:0.06
    9:0.09
    10:0.00
    11:0.01
    Negative Logits
     tee
    -2.17
    akuya
    -2.02
    DragonMagazine
    -1.96
    Christmas
    -1.94
    Iv
    -1.83
     unanimous
    -1.81
    uddenly
    -1.80
    Purchase
    -1.80
     OFFIC
    -1.79
    Shop
    -1.74
    POSITIVE LOGITS
    etics
    2.39
     Strategy
    2.32
    ometry
    2.26
    ategy
    2.11
     psychology
    2.09
    iology
    2.08
     writes
    2.08
     sociology
    2.07
     strategy
    2.04
    anchester
    2.03
    Act Density 0.031%

    No Known Activations