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

    Neuronpedia

    INDEX
    Explanations

    categories and classifications related to living organisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.05
    2:0.02
    3:0.06
    4:0.08
    5:0.45
    6:0.02
    7:0.07
    8:0.04
    9:0.02
    10:0.03
    11:0.09
    Negative Logits
     surn
    -3.42
     surname
    -3.17
     Preferred
    -3.15
     Reserv
    -3.15
     Lone
    -2.99
     Disciple
    -2.92
     designation
    -2.86
     Resident
    -2.85
     Celebrity
    -2.85
     Warrant
    -2.82
    POSITIVE LOGITS
     crib
    3.01
    azo
    2.96
    Grab
    2.83
    oros
    2.69
    paren
    2.62
    ilib
    2.60
    escal
    2.55
    ���
    2.54
    CLOSE
    2.54
     brink
    2.51
    Act Density 0.064%

    No Known Activations