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

    Neuronpedia

    INDEX
    Explanations

    statements that convey strong opinions or stances

    oai_token-act-pair · gpt-3.5-turbo

    intensifiers related to strong opinions or beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ammy
    -0.75
     slideshow
    -0.74
    RAW
    -0.68
     terribly
    -0.65
     wonderfully
    -0.65
    agically
    -0.64
     tragically
    -0.64
    gallery
    -0.63
     tremendously
    -0.62
    emetery
    -0.62
    POSITIVE LOGITS
     disagreed
    1.03
     opposed
    1.01
     opposes
    0.98
     disagree
    0.97
     oppose
    0.96
     objected
    0.93
     disagrees
    0.92
     condemns
    0.91
     disapprove
    0.90
     denies
    0.90
    Act Density 0.054%

    No Known Activations