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

    Neuronpedia

    INDEX
    Explanations

    causal relationships or attributions of various issues to specific factors

    oai_token-act-pair · gpt-3.5-turbo

    causal relationships between factors and negative health or environmental outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.92
    displayText
    -0.80
    EStreamFrame
    -0.76
    alan
    -0.75
    ĸļ
    -0.74
    ISO
    -0.72
    FTWARE
    -0.72
    AU
    -0.72
    idav
    -0.71
    Statement
    -0.71
    POSITIVE LOGITS
     poverty
    1.16
     deaths
    1.14
     crime
    1.13
     diseases
    1.13
     cancers
    1.08
     criminality
    1.07
     illnesses
    1.04
     cancer
    1.03
     impover
    1.01
     murders
    1.01
    Act Density 0.331%

    No Known Activations