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

    Neuronpedia

    INDEX
    Explanations

    words related to safety and restrictions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to safety and restrictions in human behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ptroller
    -0.71
     Defender
    -0.70
     Gleaming
    -0.70
    oiler
    -0.69
    unes
    -0.69
    maxwell
    -0.68
    ãĤ³
    -0.68
    »Ĵ
    -0.67
    warn
    -0.67
    mem
    -0.66
    POSITIVE LOGITS
     activity
    1.70
     activities
    1.66
     operation
    1.49
     operations
    1.43
     consumption
    1.35
     usage
    1.33
     use
    1.30
     participation
    1.28
     behaviour
    1.26
     employment
    1.25
    Act Density 0.451%

    No Known Activations