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

    Neuronpedia

    INDEX
    Explanations

    adverbs that emphasize the extent or degree of something

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "quite" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ULTS
    -0.84
     DRAG
    -0.77
    venant
    -0.71
    elsen
    -0.71
    owe
    -0.69
    olen
    -0.68
    orer
    -0.66
    PLIED
    -0.65
    ultimate
    -0.64
    ":"/
    -0.64
    POSITIVE LOGITS
     frankly
    1.15
     literally
    0.95
     possibly
    0.89
     alright
    0.85
     awhile
    0.81
     honestly
    0.77
     rightly
    0.71
    entimes
    0.70
     alot
    0.69
    some
    0.69
    Act Density 0.024%

    No Known Activations