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

    Neuronpedia

    INDEX
    Explanations

    mentions of possessive pronouns followed by a noun, indicating ownership or association

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "his" which indicates possessive references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibaba
    -0.82
    llular
    -0.73
    ãĥ´ãĤ¡
    -0.69
    ersed
    -0.66
    Thumbnail
    -0.65
    ÑĮ
    -0.64
    ftime
    -0.64
    Stre
    -0.64
    uded
    -0.64
    unker
    -0.64
    POSITIVE LOGITS
     colleague
    1.33
     own
    1.29
     colleagues
    1.23
     clients
    1.16
     predecessors
    1.11
     predecessor
    1.08
     constituents
    1.07
     client
    1.06
     nephew
    1.05
     superiors
    1.04
    Act Density 0.230%

    No Known Activations