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

    Neuronpedia

    INDEX
    Explanations

    references to duality or pairs in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ต่างๆ
    -0.56
    Various
    -0.51
     vários
    -0.49
     semua
    -0.48
    jenigen
    -0.48
     Various
    -0.48
     antaranya
    -0.48
     pelbagai
    -0.47
     allemaal
    -0.47
     berbagai
    -0.47
    POSITIVE LOGITS
     sides
    1.44
     sexes
    1.25
    sides
    1.14
     parties
    1.04
     halves
    1.01
     genders
    1.00
     ends
    0.98
     Sides
    0.90
    Sides
    0.88
     kinds
    0.86
    Act Density 0.220%

    No Known Activations