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

    Neuronpedia

    INDEX
    Explanations

    references to familial relationships, particularly those involving mothers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.07
    2:0.07
    3:0.08
    4:0.04
    5:0.03
    6:0.12
    7:0.06
    8:0.05
    9:0.30
    10:0.03
    11:0.03
    Negative Logits
    ��
    -3.88
     HF
    -3.62
     LX
    -3.26
    ++++
    -3.15
     Warranty
    -3.08
    hire
    -3.06
     XIV
    -3.03
     Wine
    -3.02
    icious
    -3.01
     XIII
    -2.95
    POSITIVE LOGITS
     mother
    3.94
     mom
    3.81
     parents
    3.39
     classmates
    3.34
     mum
    3.33
     Maced
    3.19
     classmate
    3.13
     Mississ
    3.06
     Columb
    3.02
     recol
    2.99
    Act Density 0.001%

    No Known Activations