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

    Neuronpedia

    INDEX
    Explanations

    references to differences or distinctions among subjects or variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sangue
    -0.49
    leştir
    -0.46
     estadia
    -0.44
     Huntingdon
    -0.44
     violência
    -0.43
     famílias
    -0.42
     correto
    -0.41
     nucléaire
    -0.41
     neque
    -0.41
    MIA
    -0.40
    POSITIVE LOGITS
     different
    1.18
    different
    1.09
     Different
    1.06
     StatelessWidget
    1.06
     differ
    1.05
    Different
    1.04
    RenderAtEndOf
    1.03
     differently
    1.03
     DIFFERENT
    0.96
     differing
    0.95
    Act Density 0.519%

    No Known Activations