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

    Neuronpedia

    INDEX
    Explanations

    comparative adjectives denoting a higher degree or amount

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate an increase or improvement in conditions or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    proxy
    -0.76
    crow
    -0.75
    missions
    -0.73
    wine
    -0.73
    elf
    -0.72
    EP
    -0.71
    codes
    -0.71
    raid
    -0.70
    dress
    -0.70
    è
    -0.70
    POSITIVE LOGITS
     than
    1.28
     emphasis
    1.17
     likelihood
    1.12
     reliance
    1.11
     flexibility
    1.09
     importance
    1.08
     prominence
    1.04
     distances
    1.03
     proportion
    1.01
     clarity
    1.00
    Act Density 0.035%

    No Known Activations