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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political discussions or statements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal or official statements and arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hindsight
    -0.84
    Plex
    -0.79
    TPPStreamerBot
    -0.75
     Paddock
    -0.72
    ulton
    -0.67
    erest
    -0.66
    çĶŁ
    -0.66
    lymp
    -0.65
    Quantity
    -0.64
     Guinness
    -0.64
    POSITIVE LOGITS
     letter
    1.33
     urged
    1.19
     urges
    1.10
     urging
    1.06
    Dear
    1.02
     wrote
    1.01
     petition
    1.00
     letters
    0.99
     demanded
    0.99
     alleges
    0.97
    Act Density 0.576%

    No Known Activations