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

    Neuronpedia

    INDEX
    Explanations

    phrases related to death and punishment

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    Datuak
    -0.62
    渥
    -0.58
    translateX
    -0.49
     Bourgoin
    -0.48
     aspi
    -0.48
     gere
    -0.45
    bewerken
    -0.45
     Opin
    -0.44
    Enllaces
    -0.44
    FactoryBean
    -0.44
    POSITIVE LOGITS
    death
    1.16
     death
    1.14
     DEATH
    1.11
    Death
    1.11
     Death
    1.10
    DEATH
    0.99
     deaths
    0.93
     Deaths
    0.90
    Deaths
    0.87
     Muerte
    0.85
    Act Density 0.085%

    No Known Activations