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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expressing opposition or criticism

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" and its context in discussions of opposition to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elaide
    -0.74
    handled
    -0.73
    ¯
    -0.70
    ï¸ı
    -0.70
    --+
    -0.68
     solves
    -0.68
     answered
    -0.68
    strate
    -0.68
     remembers
    -0.68
    restling
    -0.67
    POSITIVE LOGITS
     notion
    1.27
     idea
    1.27
     legality
    1.17
     validity
    1.11
     constitution
    1.07
     inclusion
    1.02
     imposition
    1.02
     existence
    1.02
     entirety
    0.99
     Affordable
    0.98
    Act Density 0.273%

    No Known Activations