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

    Neuronpedia

    INDEX
    Explanations

    references to individuals and their actions within a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ISIBLE
    -0.14
     ones
    -0.14
    Versions
    -0.14
     sortie
    -0.14
    ordon
    -0.14
    ly
    -0.13
    ARRIER
    -0.13
    USTOM
    -0.13
    asc
    -0.13
    routeParams
    -0.13
    POSITIVE LOGITS
     nicht
    0.26
     led
    0.26
     nie
    0.26
     ke
    0.25
     som
    0.23
     nur
    0.23
     ni
    0.23
     nir
    0.21
     mang
    0.21
     prin
    0.20
    Act Density 0.035%

    No Known Activations