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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms or configurations referred to as 'defaults'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of default settings or configurations in software documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    borough
    -1.01
    atform
    -0.84
    lehem
    -0.79
    ropolitan
    -0.78
    iddles
    -0.77
     Flavoring
    -0.74
    coni
    -0.74
    hemat
    -0.73
    andum
    -0.72
    wick
    -0.71
    POSITIVE LOGITS
     settings
    1.00
     behaviour
    0.89
     defaults
    0.87
     gateway
    0.84
     behavior
    0.83
     configuration
    0.80
    dict
    0.79
    isable
    0.79
     implementations
    0.79
     disclaimer
    0.78
    Act Density 0.021%

    No Known Activations