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

    Neuronpedia

    INDEX
    Explanations

    references to socks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    sockssockhosiery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ıştır
    -0.38
    Chham
    -0.37
    ibatis
    -0.35
    richTextPanel
    -0.35
     Grenville
    -0.34
     Williamson
    -0.34
    ритори
    -0.34
     Hauser
    -0.32
     Ren
    -0.32
     Markham
    -0.32
    POSITIVE LOGITS
     socks
    2.19
     Socks
    2.11
    Socks
    1.82
    socks
    1.66
     sock
    1.48
     Sock
    1.48
     calcetines
    1.44
    Sock
    1.30
     chaus
    1.18
     SOCK
    1.16
    Act Density 0.002%

    No Known Activations