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

    Neuronpedia

    INDEX
    Explanations

    word combinations related to programming and memory allocation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    technical terms related to C++ programming, particularly in defining and manipulating strings and allocators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.04
    2:0.15
    3:0.11
    4:0.16
    5:0.05
    6:0.05
    7:0.02
    8:0.07
    9:0.15
    10:0.06
    11:0.03
    Negative Logits
     Mug
    -1.34
     Ü
    -1.32
     HIM
    -1.32
    othal
    -1.28
    Topic
    -1.23
     Spa
    -1.22
     HOT
    -1.20
     Him
    -1.20
     Wonderland
    -1.20
     Tow
    -1.20
    POSITIVE LOGITS
    reference
    1.59
     Sturgeon
    1.35
     filibuster
    1.31
    repeat
    1.31
    error
    1.30
    Dispatch
    1.29
    adder
    1.29
     pse
    1.29
    merce
    1.28
    Compar
    1.26
    Act Density 0.003%

    No Known Activations