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

    Neuronpedia

    INDEX
    Explanations

    prepositions and conjunctions used to indicate relationships between ideas and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bu
    -0.18
    inner
    -0.15
    jl
    -0.15
    را
    -0.15
    zc
    -0.14
    ss
    -0.14
    angan
    -0.14
    onga
    -0.14
     eu
    -0.14
    bb
    -0.14
    POSITIVE LOGITS
     Hib
    0.17
    ocab
    0.17
    createClass
    0.16
    deaux
    0.15
    DOI
    0.15
    ãģĵãģĨ
    0.14
    NECT
    0.14
    GLOSS
    0.14
    edx
    0.14
    elper
    0.14
    Act Density 0.522%

    No Known Activations