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

    Neuronpedia

    INDEX
    Explanations

    verbs and other action-oriented words emphasizing completion or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cro
    -0.18
    eya
    -0.18
    Cro
    -0.18
    áze
    -0.17
    cro
    -0.16
    iÃŃ
    -0.15
    ergus
    -0.15
    buch
    -0.15
    ÙĪص
    -0.15
    _counters
    -0.15
    POSITIVE LOGITS
     rel
    0.15
    -pic
    0.14
    ena
    0.14
    à¥įरथ
    0.14
     Peters
    0.14
    elli
    0.14
    -rel
    0.14
    Pic
    0.14
     loc
    0.14
    tle
    0.14
    Act Density 0.003%

    No Known Activations