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

    Neuronpedia

    INDEX
    Explanations

    references to the intricacies of life and personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     graphs
    -0.15
    graphs
    -0.15
     charts
    -0.14
     Packs
    -0.14
    ABILITY
    -0.14
     interruption
    -0.14
    Maps
    -0.14
    ailure
    -0.14
    Videos
    -0.14
    azard
    -0.14
    POSITIVE LOGITS
     joys
    0.30
     satisf
    0.29
     pleasures
    0.27
     sor
    0.26
     foll
    0.25
     lux
    0.25
     anx
    0.24
     comforts
    0.24
     cares
    0.24
     enthus
    0.23
    Act Density 0.201%

    No Known Activations