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

    Neuronpedia

    INDEX
    Explanations

    elements related to data manipulation and processing functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.06
    2:0.33
    3:0.03
    4:0.02
    5:0.04
    6:0.06
    7:0.05
    8:0.05
    9:0.04
    10:0.17
    11:0.06
    Negative Logits
    rie
    -2.68
    favorite
    -2.58
    obo
    -2.55
    roach
    -2.48
    ictionary
    -2.48
     Trader
    -2.48
    jer
    -2.43
    rette
    -2.32
    obbies
    -2.31
    iera
    -2.30
    POSITIVE LOGITS
     X
    4.30
     NX
    3.68
    X
    3.57
     Xen
    3.44
     IX
    2.99
     XML
    2.78
     XT
    2.69
     XD
    2.66
     Indigo
    2.63
     Pix
    2.62
    Act Density 0.001%

    No Known Activations