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

    Neuronpedia

    INDEX
    Explanations

    references to programming concepts or terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.07
    2:0.09
    3:0.08
    4:0.08
    5:0.09
    6:0.07
    7:0.07
    8:0.07
    9:0.08
    10:0.09
    11:0.07
    Negative Logits
     Armen
    -2.89
    endi
    -2.85
     Amon
    -2.74
     Moroccan
    -2.72
     Armenia
    -2.57
    atron
    -2.52
     Morocco
    -2.52
     Tasman
    -2.48
     Anthem
    -2.43
     Gamb
    -2.38
    POSITIVE LOGITS
     Definition
    2.88
    ilk
    2.60
     IPM
    2.52
     TOD
    2.52
     condem
    2.47
     ls
    2.46
    orpor
    2.44
     Definitions
    2.43
     Sail
    2.43
     Slug
    2.42
    Act Density 0.000%

    No Known Activations