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

    Neuronpedia

    INDEX
    Explanations

    references to specific locations and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.04
    2:0.12
    3:0.12
    4:0.02
    5:0.04
    6:0.08
    7:0.09
    8:0.15
    9:0.05
    10:0.09
    11:0.12
    Negative Logits
    azeera
    -1.19
    nces
    -1.13
    redit
    -1.09
    yss
    -1.05
    amins
    -1.03
    verb
    -1.00
    pointers
    -1.00
    ormons
    -0.99
    imil
    -0.98
    ept
    -0.98
    POSITIVE LOGITS
     midst
    1.17
     vicinity
    1.10
     Basin
    0.99
     intest
    0.96
     nets
    0.96
     encl
    0.96
     behalf
    0.96
     Ku
    0.93
     FI
    0.92
     Wake
    0.91
    Act Density 0.150%

    No Known Activations