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

    Neuronpedia

    INDEX
    Explanations

    references to concepts related to identity, particularly in the context of cultural or ethnic backgrounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.12
    1:0.11
    2:0.05
    3:0.12
    4:0.05
    5:0.02
    6:0.07
    7:0.14
    8:0.03
    9:0.05
    10:0.12
    11:0.06
    Negative Logits
     Tuls
    -3.06
    Ohio
    -2.69
     Kass
    -2.46
    phis
    -2.45
     recomm
    -2.43
     Kris
    -2.35
    Indiana
    -2.34
     Pengu
    -2.32
     Kasich
    -2.31
    ajor
    -2.28
    POSITIVE LOGITS
     Anglo
    6.00
     Viking
    3.57
    Sax
    3.40
     Sax
    3.19
     pagan
    2.89
     Scandinavian
    2.89
     Medieval
    2.88
     Elven
    2.86
     Nordic
    2.65
     Pagan
    2.63
    Act Density 0.001%

    No Known Activations