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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions that justify or defend a decision

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and sentence breaks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     thrill
    -0.65
     unicorn
    -0.62
    plet
    -0.62
     oath
    -0.61
    itialized
    -0.61
     strap
    -0.60
     awesome
    -0.60
    ersive
    -0.60
    ierre
    -0.59
     planet
    -0.59
    POSITIVE LOGITS
    Newsletter
    1.39
    Advertisement
    0.98
    Similarly
    0.95
    Finally
    0.91
    Copyright
    0.90
    Meanwhile
    0.89
    Lastly
    0.87
    VERTISEMENT
    0.87
    Write
    0.87
    Still
    0.85
    Act Density 0.514%

    No Known Activations