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

    Neuronpedia

    INDEX
    Explanations

    terms related to data filtering and processing operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    391
    -0.15
    ificent
    -0.15
    -Core
    -0.14
    622
    -0.14
    å¸Ń
    -0.14
    ικÏİν
    -0.14
    LocalizedString
    -0.14
    ecure
    -0.13
    ãģ£
    -0.13
    884
    -0.13
    POSITIVE LOGITS
     specifically
    0.19
     filtering
    0.17
    iane
    0.17
     çŃ
    0.17
     bestimm
    0.17
     certain
    0.17
    filter
    0.16
    needle
    0.16
     Certain
    0.16
     Specifically
    0.16
    Act Density 0.297%

    No Known Activations