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

    Neuronpedia

    INDEX
    Explanations

    words related to superlatives or extremes

    oai_token-act-pair · gpt-3.5-turbo

    key terms associated with high-impact concepts or extreme conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Decoder
    -0.75
     Jackets
    -0.66
     Dragons
    -0.65
     Waves
    -0.65
     flats
    -0.62
     Writers
    -0.62
     Pax
    -0.60
     Generator
    -0.60
     Growth
    -0.60
     waivers
    -0.59
    POSITIVE LOGITS
    fficient
    1.06
    erous
    1.05
    icable
    1.05
    accessible
    1.04
    isable
    1.04
    icent
    1.03
    istic
    1.02
    ifiable
    1.01
    ivable
    1.01
    isible
    1.01
    Act Density 0.331%

    No Known Activations