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

    Neuronpedia

    INDEX
    Explanations

    the word "it" occurring at the end of a sentence

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize finality or conclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tokyo
    -0.73
     Seoul
    -0.68
     compliment
    -0.66
     QUEST
    -0.62
     Jag
    -0.62
     Japan
    -0.61
     excerpts
    -0.60
     Japanese
    -0.59
     Somalia
    -0.59
     Flav
    -0.58
    POSITIVE LOGITS
    chy
    1.10
    atically
    1.07
    eding
    1.06
    eded
    0.97
    pher
    0.97
    aning
    0.92
    vern
    0.91
    atic
    0.90
    athered
    0.90
    aned
    0.90
    Act Density 0.348%

    No Known Activations