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

    Neuronpedia

    INDEX
    Explanations

    phrases related to programming, specifically function calls and code execution

    oai_token-act-pair · gpt-3.5-turbo

    references to conditional statements or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    packs
    -0.74
    ppa
    -0.71
    ourced
    -0.71
    ixels
    -0.69
    Americans
    -0.69
    worth
    -0.68
    izons
    -0.68
    grown
    -0.67
    shirts
    -0.67
    ourcing
    -0.67
    POSITIVE LOGITS
     procedure
    1.08
     tests
    1.03
     procedures
    1.02
     calculations
    0.98
     diagnostic
    0.97
     tasks
    0.97
     commands
    0.96
     computation
    0.94
     maneuvers
    0.94
     calculation
    0.91
    Act Density 0.452%

    No Known Activations