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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the extent or range of something

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of 'scope' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    maid
    -0.73
     Valentine
    -0.68
    ocard
    -0.67
    ublic
    -0.66
     pengu
    -0.62
    ston
    -0.61
    eah
    -0.60
    tons
    -0.59
     Zimmer
    -0.58
    Tickets
    -0.58
    POSITIVE LOGITS
     scope
    1.10
     Scope
    0.91
     creep
    0.80
    Scope
    0.80
    illary
    0.79
    witz
    0.78
    ifi
    0.74
    izons
    0.73
    mares
    0.72
    xes
    0.72
    Act Density 0.023%

    No Known Activations