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

    Neuronpedia

    INDEX
    Explanations

    the concept of something being "built-in"

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to features or components that are built into devices or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mub
    -0.85
    anches
    -0.79
    CENT
    -0.78
    kk
    -0.75
    Ń·
    -0.74
    ĸļ
    -0.73
     Bought
    -0.72
    Ĥª
    -0.72
     Rebell
    -0.72
    =-=-=-=-
    -0.71
    POSITIVE LOGITS
    jury
    0.88
     complication
    0.84
     auto
    0.79
     compliance
    0.78
     functionality
    0.77
     accessibility
    0.77
     extras
    0.74
     support
    0.74
     mechanism
    0.71
     redundancy
    0.70
    Act Density 0.030%

    No Known Activations