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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating possession or attribution in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Them
    -0.17
     Them
    -0.17
     Proud
    -0.15
    001
    -0.14
    çĵľ
    -0.14
    ilan
    -0.14
     Himself
    -0.14
    lie
    -0.14
    YNC
    -0.14
     fruition
    -0.13
    POSITIVE LOGITS
     being
    0.31
     having
    0.23
    being
    0.22
     Being
    0.20
    Being
    0.19
     how
    0.19
     among
    0.19
     contributions
    0.18
     always
    0.18
     essere
    0.18
    Act Density 0.053%

    No Known Activations