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

    Neuronpedia

    INDEX
    Explanations

    instances of high emotional intensity expressed as an adverb emphasizing the speaker's feelings

    oai_token-act-pair · gpt-3.5-turbo

    intensifiers or adverbs that indicate strong emotions or states of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     occurs
    -0.76
     originate
    -0.71
    ulence
    -0.70
    glers
    -0.69
     undermines
    -0.68
     lasts
    -0.68
     arises
    -0.68
     derives
    -0.67
     translates
    -0.67
     predicate
    -0.66
    POSITIVE LOGITS
     aware
    1.17
     thankful
    1.14
     glad
    1.12
     proud
    1.09
     fortunate
    1.06
     lucky
    1.05
     happy
    1.01
     grateful
    1.01
     afraid
    1.00
     wondering
    0.98
    Act Density 0.297%

    No Known Activations