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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating authority or official action

    oai_token-act-pair · gpt-3.5-turbo

    references to authority or official matters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    here
    -0.84
    ipedia
    -0.72
    reviewed
    -0.72
    iy
    -0.72
    herer
    -0.71
     with
    -0.70
    lass
    -0.69
    raf
    -0.68
    packing
    -0.68
    assetsadobe
    -0.67
    POSITIVE LOGITS
     exception
    1.73
     intention
    1.39
     caveat
    1.33
     help
    1.31
     aim
    1.18
     utmost
    1.18
     intent
    1.18
     assistance
    1.16
     aid
    1.09
     expectation
    1.09
    Act Density 0.177%

    No Known Activations