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

    Neuronpedia

    INDEX
    Explanations

    common conjunctions and prepositions, indicating relational connections within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arel
    -0.18
    renom
    -0.16
     Nunes
    -0.16
    ardi
    -0.15
    unas
    -0.15
    bon
    -0.15
    اتر
    -0.15
    Ỽi
    -0.14
    aje
    -0.14
     poc
    -0.14
    POSITIVE LOGITS
    asher
    0.17
    جÙĩ
    0.16
    abinet
    0.16
    .nr
    0.15
    ument
    0.15
    dire
    0.15
    hlas
    0.14
    ATIO
    0.14
    abis
    0.14
    ialog
    0.14
    Act Density 0.003%

    No Known Activations