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

    Neuronpedia

    INDEX
    Explanations

    pronouns (his, her, it) followed by possessive adjectives (such as 'his,' 'her,' etc.) referring to a specific person

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns, particularly "his" and "her."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umblr
    -0.79
    ibaba
    -0.76
    igslist
    -0.74
    llular
    -0.73
    ĸļ
    -0.71
    ?????-
    -0.69
    ãĥ´ãĤ¡
    -0.68
    urations
    -0.68
    igham
    -0.68
    ersed
    -0.67
    POSITIVE LOGITS
     colleague
    1.45
     own
    1.33
     colleagues
    1.25
     daughter
    1.21
     son
    1.21
     nephew
    1.19
     granddaughter
    1.14
     predecessor
    1.14
     constituents
    1.14
     client
    1.14
    Act Density 0.290%

    No Known Activations