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

    Neuronpedia

    INDEX
    Explanations

    references to cannibalism and survival themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ations
    -0.18
     Kirk
    -0.17
    ergus
    -0.16
    arus
    -0.16
    vie
    -0.16
    avin
    -0.16
    asis
    -0.16
    inus
    -0.16
    atively
    -0.16
     McCl
    -0.15
    POSITIVE LOGITS
    ená
    0.19
    estado
    0.18
    olars
    0.18
    earn
    0.18
    ñ
    0.18
    idata
    0.18
    eg
    0.17
    iná
    0.17
    uada
    0.17
    dados
    0.17
    Act Density 0.040%

    No Known Activations