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

    Neuronpedia

    INDEX
    Explanations

    key phrases related to significant concepts and themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.02
    2:0.09
    3:0.13
    4:0.25
    5:0.02
    6:0.17
    7:0.04
    8:0.05
    9:0.03
    10:0.05
    11:0.05
    Negative Logits
    ctors
    -1.67
    ophers
    -1.40
     trolls
    -1.38
    efficients
    -1.37
     guards
    -1.29
    ukemia
    -1.27
    iatrics
    -1.25
    appers
    -1.25
    gdala
    -1.24
    chers
    -1.23
    POSITIVE LOGITS
    ディ
    1.51
    ��
    1.50
    ��
    1.46
    ゼ
    1.37
    marked
    1.34
     intended
    1.31
    ��
    1.30
     lasting
    1.30
    ヴァ
    1.27
    Present
    1.26
    Act Density 0.074%

    No Known Activations