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

    Neuronpedia

    INDEX
    Explanations

    prepositions or conjunctions followed by specific words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the concept of time or location within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    76561
    -0.67
     ®
    -0.67
    aic
    -0.65
    ãĤ´ãĥ³
    -0.64
    erenn
    -0.64
    ARE
    -0.64
     penned
    -0.63
    ä
    -0.63
    soever
    -0.62
    umed
    -0.61
    POSITIVE LOGITS
     terms
    1.23
     my
    1.14
     regards
    1.13
     somew
    1.09
     hindsight
    1.04
     retrospect
    1.01
     spite
    0.97
     relation
    0.97
    terms
    0.90
     vain
    0.88
    Act Density 0.248%

    No Known Activations