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

    Neuronpedia

    INDEX
    Explanations

    adjectives used to describe something as very large or intense

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey magnitude or scale

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cents
    -0.71
    istrates
    -0.71
     occasional
    -0.70
     Bye
    -0.69
     Concern
    -0.67
    idge
    -0.66
    onyms
    -0.66
    stick
    -0.66
     inconsist
    -0.66
    iquette
    -0.66
    POSITIVE LOGITS
     unparalleled
    1.08
     unimaginable
    1.07
     trillions
    0.97
     unbelievable
    0.95
     colossal
    0.94
     feats
    0.94
     astounding
    0.93
     unprecedented
    0.92
     unmatched
    0.92
     incredible
    0.92
    Act Density 1.098%

    No Known Activations