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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns indicating ownership or association

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and associated references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ved
    -0.76
    xon
    -0.73
    edin
    -0.72
     Activate
    -0.71
     Twain
    -0.71
    hari
    -0.70
    endif
    -0.69
     Originally
    -0.67
     Unsure
    -0.65
    zzle
    -0.65
    POSITIVE LOGITS
     sake
    1.78
     purposes
    1.42
     own
    1.24
     reasons
    1.09
     purpose
    1.01
     upcoming
    0.99
    ummies
    0.96
     liking
    0.96
     convenience
    0.94
     respective
    0.90
    Act Density 0.109%

    No Known Activations