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

    Neuronpedia

    INDEX
    Explanations

    medical conditions and statistics related to health

    oai_token-act-pair · gpt-3.5-turbo

    mentions of serious health incidents or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     directions
    -0.75
     Pledge
    -0.71
     pillars
    -0.71
    âķIJ
    -0.67
     restructuring
    -0.65
     DLC
    -0.65
     renegoti
    -0.65
    align
    -0.64
     Patreon
    -0.64
    ocracy
    -0.63
    POSITIVE LOGITS
     fatalities
    1.19
     occurrence
    1.12
     sightings
    1.05
     cases
    1.04
     rare
    1.00
     deaths
    0.99
     unlucky
    0.99
     incidence
    0.97
     incidents
    0.97
     occurrences
    0.96
    Act Density 1.306%

    No Known Activations