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

    Neuronpedia

    INDEX
    Explanations

    references to events or discussions happening in a conference setting

    oai_token-act-pair · gpt-3.5-turbo

    references to conferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ter
    -0.77
    pie
    -0.69
    tera
    -0.69
    terday
    -0.68
    ````
    -0.65
    isu
    -0.65
    ionage
    -0.64
     Pwr
    -0.64
    isons
    -0.63
    cher
    -0.63
    POSITIVE LOGITS
     convened
    0.99
     room
    0.96
     attendees
    0.94
    ference
    0.88
    eers
    0.87
     rooms
    0.86
     committee
    0.86
    room
    0.86
    ivals
    0.81
     keynote
    0.80
    Act Density 0.027%

    No Known Activations