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

    Neuronpedia

    INDEX
    Explanations

    pronouns 'they' paired with verbs indicating actions or states

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the pronoun "they."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Eps
    -0.77
     Cumber
    -0.70
     Courier
    -0.66
     Vine
    -0.63
     Hunting
    -0.62
     Cobb
    -0.62
     Burg
    -0.62
     Wol
    -0.62
     Phi
    -0.62
     Vog
    -0.62
    POSITIVE LOGITS
    've
    1.18
    'd
    1.16
    're
    1.09
    selves
    0.97
    zbollah
    0.88
     appre
    0.88
    'll
    0.88
     tasted
    0.87
     encount
    0.87
     disapprove
    0.85
    Act Density 0.078%

    No Known Activations