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

    Neuronpedia

    INDEX
    Explanations

    specific conjunctions and pronouns in various languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.59
    zugs
    -0.50
     SEG
    -0.50
    blatt
    -0.48
    ungs
    -0.47
    Kjelder
    -0.46
    Aos
    -0.46
    RuleContext
    -0.46
    omez
    -0.46
    inah
    -0.45
    POSITIVE LOGITS
     и
    1.91
     і
    1.23
     và
    1.14
     και
    1.13
     și
    1.03
    และ
    1.03
     или
    0.95
     और
    0.91
     şi
    0.90
     és
    0.87
    Act Density 0.025%

    No Known Activations