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

    Neuronpedia

    INDEX
    Explanations

    opinions or statements made by people

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate people's opinions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nton
    -0.67
     resumed
    -0.65
    ubric
    -0.64
    ailability
    -0.64
     Written
    -0.63
    arious
    -0.63
    andestine
    -0.62
    acted
    -0.61
    syn
    -0.60
     ratified
    -0.60
    POSITIVE LOGITS
     excuses
    0.77
     incorrectly
    0.73
    mares
    0.72
    assetsadobe
    0.69
     arrogance
    0.67
     ignorance
    0.66
     misconceptions
    0.66
     underest
    0.66
    cms
    0.65
     myths
    0.65
    Act Density 0.334%

    No Known Activations