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

    Neuronpedia

    INDEX
    Explanations

    phrases that start with the word "They"

    oai_token-act-pair · gpt-3.5-turbo

    references to a group or collective subject, specifically the word "They"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¿½
    -0.73
    CCC
    -0.63
    reads
    -0.62
     srfAttach
    -0.62
    JD
    -0.57
    tains
    -0.56
    pires
    -0.56
    VW
    -0.56
    Rating
    -0.54
    Offline
    -0.54
    POSITIVE LOGITS
    're
    1.57
    've
    1.24
    mos
    1.08
    'll
    1.07
     weren
    1.07
     aren
    1.04
     are
    1.03
     were
    1.00
     say
    1.00
     deserve
    0.99
    Act Density 0.252%

    No Known Activations