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

    Neuronpedia

    INDEX
    Explanations

    references to social and political injustices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _utilities
    -0.16
    極
    -0.16
     VERY
    -0.14
    ãģĭãģª
    -0.14
    oret
    -0.14
     arguably
    -0.14
    odi
    -0.14
     neither
    -0.14
    vero
    -0.13
    uno
    -0.13
    POSITIVE LOGITS
     somehow
    0.60
     Somehow
    0.32
     supposedly
    0.30
     magically
    0.30
     Ñıк
    0.27
     allegedly
    0.26
     supposed
    0.23
     suddenly
    0.23
     myster
    0.23
     blah
    0.21
    Act Density 0.830%

    No Known Activations