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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "of" indicating relationships, ownership, or description

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.17
    3:0.09
    4:0.11
    5:0.04
    6:0.06
    7:0.20
    8:0.04
    9:0.03
    10:0.05
    11:0.14
    Negative Logits
     incorpor
    -1.40
    Interstitial
    -1.40
     Bapt
    -1.34
    ��
    -1.33
    soever
    -1.31
     furn
    -1.25
     embod
    -1.25
    Stud
    -1.23
    ��
    -1.22
    ワ
    -1.21
    POSITIVE LOGITS
    rame
    1.47
    inka
    1.34
     glitch
    1.32
    ère
    1.27
    lean
    1.26
     retracted
    1.26
    rawler
    1.25
    itiveness
    1.23
    ossibility
    1.22
    =#
    1.21
    Act Density 0.002%

    No Known Activations