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

    Neuronpedia

    INDEX
    Explanations

    adverbs related to time

    oai_token-act-pair · gpt-3.5-turbo

    frequency and intensity of adverbial modifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Seym
    -0.71
     ÂŃ
    -0.63
     Coke
    -0.60
    ollar
    -0.60
     Central
    -0.59
     Organization
    -0.58
    istani
    -0.56
     Cohen
    -0.56
    eca
    -0.56
     Pav
    -0.56
    POSITIVE LOGITS
     sucks
    0.92
     refers
    0.91
     doesnt
    0.90
     depends
    0.84
     enhances
    0.83
     qualifies
    0.83
     contains
    0.82
     behaves
    0.81
     exists
    0.81
     implies
    0.80
    Act Density 0.180%

    No Known Activations