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

    Neuronpedia

    INDEX
    Explanations

    concepts related to capitalism and social class dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.03
    2:0.15
    3:0.15
    4:0.05
    5:0.14
    6:0.04
    7:0.09
    8:0.10
    9:0.03
    10:0.03
    11:0.03
    Negative Logits
     Radar
    -2.67
     mascara
    -2.48
     Flare
    -2.33
    DCS
    -2.18
     Buzz
    -2.16
    Buzz
    -2.11
     Matte
    -2.09
     Glow
    -2.07
    uberty
    -2.03
     Cancer
    -2.03
    POSITIVE LOGITS
     hierarchical
    3.25
     capitalist
    3.20
     democratically
    3.17
     societies
    3.16
     statist
    3.15
     coercive
    3.07
     commons
    3.07
     hierarch
    3.05
     monopol
    3.05
     economies
    3.04
    Act Density 1.166%

    No Known Activations