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

    Neuronpedia

    INDEX
    Explanations

    adverbs related to the extent or degree of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing widespread acceptance or recognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agate
    -0.67
     Farmers
    -0.66
    ÄŁ
    -0.64
    anth
    -0.63
    eki
    -0.61
     Patreon
    -0.61
    atto
    -0.60
     Engineers
    -0.60
    levels
    -0.60
    heny
    -0.59
    POSITIVE LOGITS
     regarded
    1.24
     admired
    1.16
     viewed
    1.14
     accepted
    1.07
     appreciated
    1.07
     misunderstood
    1.06
     circulated
    1.06
     acclaimed
    1.06
     believed
    1.05
     despised
    1.04
    Act Density 0.057%

    No Known Activations