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

    Neuronpedia

    INDEX
    Explanations

    narrative elements involving characters and their interactions in a story

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     weren
    -0.23
     estaba
    -0.21
     were
    -0.21
     yoktu
    -0.21
     étaient
    -0.21
     estava
    -0.19
     бÑĭли
    -0.19
     vardı
    -0.19
     ήÏĦαν
    -0.19
     était
    -0.18
    POSITIVE LOGITS
     does
    0.26
    íķľëĭ¤
    0.24
     íķľëĭ¤
    0.23
    иваеÑĤÑģÑı
    0.22
    ëIJľëĭ¤
    0.21
    ëĬĶëĭ¤
    0.21
     becomes
    0.20
    does
    0.20
     DOES
    0.20
     goes
    0.20
    Act Density 0.121%

    No Known Activations