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

    Neuronpedia

    INDEX
    Explanations

    information related to research studies and reports

    oai_token-act-pair · gpt-3.5-turbo

    references to studies and reports in research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Horus
    -0.64
     actionGroup
    -0.62
    iencies
    -0.62
    ivas
    -0.62
    (-
    -0.62
    NetMessage
    -0.61
    headers
    -0.60
     Blades
    -0.58
    animate
    -0.58
    artifacts
    -0.57
    POSITIVE LOGITS
     commissioned
    0.80
     published
    0.77
     titled
    0.75
     conducted
    0.71
     released
    0.70
     analys
    0.69
     funded
    0.69
     declass
    0.69
     researcher
    0.69
     entitled
    0.68
    Act Density 0.165%

    No Known Activations