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

    Neuronpedia

    INDEX
    Explanations

    references to the word "speeches"

    oai_token-act-pair · gpt-3.5-turbo

    references to paid speeches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    runs
    -0.73
    appropriate
    -0.71
     Wonderland
    -0.68
     Nation
    -0.68
    Tier
    -0.67
    Captain
    -0.66
    Kay
    -0.63
    avery
    -0.62
    abol
    -0.62
     Grimm
    -0.61
    POSITIVE LOGITS
     speeches
    1.52
     lectures
    0.87
    esta
    0.85
     concerts
    0.83
    clinton
    0.81
     vows
    0.78
     seminars
    0.78
     memos
    0.78
     announcements
    0.78
     pitches
    0.77
    Act Density 0.014%

    No Known Activations