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

    Neuronpedia

    INDEX
    Explanations

    conjunctions, particularly "and," that connect ideas or clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sson
    -0.18
    ctor
    -0.15
    761
    -0.15
    orst
    -0.14
    orm
    -0.14
    iani
    -0.14
     Rank
    -0.14
     Claw
    -0.14
    905
    -0.14
    868
    -0.14
    POSITIVE LOGITS
    uji
    0.16
    adu
    0.16
    ÙĪست
    0.15
    uta
    0.15
    opa
    0.14
    ео
    0.14
    unga
    0.14
    jong
    0.14
    rega
    0.14
    atern
    0.14
    Act Density 0.009%

    No Known Activations