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

    Neuronpedia

    INDEX
    Explanations

    references to links or URLs in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.10
    3:0.08
    4:0.10
    5:0.03
    6:0.06
    7:0.21
    8:0.04
    9:0.05
    10:0.12
    11:0.11
    Negative Logits
     Cul
    -1.37
    VERTISEMENT
    -1.35
    ��
    -1.35
     Cookie
    -1.35
     Lomb
    -1.33
     Flavor
    -1.32
     Pt
    -1.31
     corners
    -1.26
     Barg
    -1.26
     Cummings
    -1.23
    POSITIVE LOGITS
    uana
    1.30
     esche
    1.29
    ukemia
    1.28
    xit
    1.28
    VK
    1.26
    reverse
    1.23
    sharing
    1.20
    shared
    1.20
    cert
    1.20
    oubted
    1.20
    Act Density 0.001%

    No Known Activations