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

    Neuronpedia

    INDEX
    Explanations

    references to societal issues and the implications of social structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.05
    2:0.03
    3:0.03
    4:0.03
    5:0.47
    6:0.02
    7:0.02
    8:0.05
    9:0.08
    10:0.08
    11:0.04
    Negative Logits
    wagen
    -2.13
    qt
    -2.12
    selage
    -2.09
    wo
    -2.07
    eca
    -2.00
    osa
    -1.94
    orah
    -1.94
    xi
    -1.93
    ela
    -1.90
    thens
    -1.90
    POSITIVE LOGITS
     respons
    2.37
     notions
    2.21
     considerations
    2.16
     bias
    2.09
     affinity
    2.07
     supportive
    2.06
     interests
    2.04
     expectations
    2.00
     patronage
    1.99
     oppos
    1.99
    Act Density 0.237%

    No Known Activations