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

    Neuronpedia

    INDEX
    Explanations

    hyphenated expressions related to percentages

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to percentages and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     laure
    -0.77
     cheated
    -0.68
     rejoice
    -0.66
     patriotism
    -0.64
     prevailed
    -0.62
     Piercing
    -0.61
     Owl
    -0.61
     Wiley
    -0.60
     collided
    -0.60
     fray
    -0.60
    POSITIVE LOGITS
    package
    0.95
    prem
    0.92
    elect
    0.92
    album
    0.91
    standard
    0.90
    average
    0.88
    minute
    0.85
    dollar
    0.85
    year
    0.85
    pair
    0.84
    Act Density 0.048%

    No Known Activations