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

    Neuronpedia

    INDEX
    Explanations

    specific dates or time-related events

    oai_token-act-pair · gpt-3.5-turbo

    references to current events and news-related discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Native
    -0.74
    apter
    -0.73
    $.
    -0.70
     Defendants
    -0.70
     foreclosure
    -0.69
     someday
    -0.67
     Plaintiff
    -0.67
    TOR
    -0.66
    Columb
    -0.64
    Years
    -0.64
    POSITIVE LOGITS
     apologised
    0.95
     criticised
    0.94
     spokesman
    0.93
     congratulated
    0.90
     meanwhile
    0.83
     reacted
    0.83
     angrily
    0.81
     spokeswoman
    0.80
     condem
    0.79
    iannopoulos
    0.77
    Act Density 0.775%

    No Known Activations