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

    Neuronpedia

    INDEX
    Explanations

    phrases related to occurrences or events taking place

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     réaliste
    -0.61
    seamnă
    -0.59
     détru
    -0.57
     démocr
    -0.57
     colorés
    -0.56
     trouvez
    -0.56
    fört
    -0.56
     Escribe
    -0.55
     normaux
    -0.54
     détruit
    -0.54
    POSITIVE LOGITS
     going
    1.04
    Going
    1.03
    going
    0.96
     taking
    0.92
    Taking
    0.89
     GOING
    0.89
     Going
    0.87
    GOING
    0.86
     making
    0.85
     Taking
    0.83
    Act Density 0.131%

    No Known Activations