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

    Neuronpedia

    INDEX
    Explanations

    dates and events

    oai_token-act-pair · gpt-3.5-turbo

    references to meetings or conferences and their associated details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     selves
    -0.67
     havoc
    -0.64
    hirt
    -0.64
     cling
    -0.62
     steals
    -0.59
     smugg
    -0.59
     dearly
    -0.59
    Simply
    -0.58
    psons
    -0.58
    makes
    -0.57
    POSITIVE LOGITS
     chaired
    1.35
     convened
    1.34
     hosted
    1.24
     attended
    1.22
     presided
    1.20
     organised
    1.18
     organized
    1.05
     moder
    1.03
     sponsored
    1.02
     titled
    0.99
    Act Density 0.340%

    No Known Activations