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

    Neuronpedia

    INDEX
    Explanations

    prepositions and conjunctions

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and phrases indicating relationships or connections between different entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     consulted
    -0.35
    ulous
    -0.34
    orah
    -0.34
    ŀ
    -0.32
    named
    -0.32
    uart
    -0.32
     succeeded
    -0.32
    igible
    -0.31
    vic
    -0.31
     billed
    -0.30
    POSITIVE LOGITS
     our
    0.34
     bip
    0.33
     the
    0.33
    imity
    0.31
     Rin
    0.31
     Shutterstock
    0.30
     regards
    0.30
     Pastebin
    0.30
     halftime
    0.29
     another
    0.28
    Act Density 1.743%

    No Known Activations