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

    Neuronpedia

    INDEX
    Explanations

    warnings about health risks and potential medical issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vées
    -0.59
    ReusableCell
    -0.53
    atigable
    -0.51
    IVIA
    -0.47
     AssemblyTitle
    -0.47
    
    -0.45
    transpiration
    -0.44
    สัม
    -0.44
     csal
    -0.44
    ourite
    -0.43
    POSITIVE LOGITS
     serious
    1.30
     dangerous
    1.17
     Serious
    1.10
    Serious
    1.10
    serious
    1.09
     seriousness
    1.05
     danger
    1.03
     Danger
    1.02
    dangerous
    0.99
     catastrophic
    0.93
    Act Density 0.380%

    No Known Activations