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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences describing situations or characteristics in a negative or critical light

    oai_token-act-pair · gpt-3.5-turbo

    references to painting or depicting situations, conditions, or characteristics through figurative language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    staking
    -0.68
    lease
    -0.68
    amba
    -0.67
    orship
    -0.67
    utenberg
    -0.66
    atches
    -0.66
    iencies
    -0.63
    arthed
    -0.63
    otrop
    -0.63
     reproduce
    -0.61
    POSITIVE LOGITS
     bleak
    0.81
     differently
    0.78
    TextColor
    0.75
     gloom
    0.74
     picture
    0.72
     vividly
    0.69
     Draper
    0.69
     gloomy
    0.68
     dystopian
    0.67
     portrait
    0.67
    Act Density 0.288%

    No Known Activations