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

    Neuronpedia

    INDEX
    Explanations

    references to individuals and their interactions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sahiptir
    -0.50
     göre
    -0.47
    ########.
    -0.45
    意思是
    -0.45
    しまいました
    -0.44
     Để
    -0.44
    found
    -0.43
     nên
    -0.43
     faptul
    -0.42
     oublier
    -0.41
    POSITIVE LOGITS
     unfold
    1.06
     coming
    0.93
     emerge
    0.93
     evolve
    0.90
     firsthand
    0.85
     unfolding
    0.84
     happening
    0.81
     flourish
    0.81
     للمعارف
    0.80
     flourishing
    0.80
    Act Density 0.201%

    No Known Activations