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

    Neuronpedia

    INDEX
    Explanations

    personal actions and belongings

    oai_token-act-pair · gpt-3.5-turbo

    references to specific items or features related to personal experiences and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ANS
    -0.80
    anas
    -0.72
    AN
    -0.72
     AN
    -0.71
     emanc
    -0.70
    Lex
    -0.70
     ACTIONS
    -0.70
    Austral
    -0.69
    TPPStreamerBot
    -0.68
    accompan
    -0.68
    POSITIVE LOGITS
     box
    1.05
     knob
    0.93
     disk
    0.92
    naire
    0.92
     Grid
    0.90
     grid
    0.90
     Box
    0.90
     table
    0.89
     tablet
    0.87
     tube
    0.87
    Act Density 0.367%

    No Known Activations