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

    Neuronpedia

    INDEX
    Explanations

    references to possession or relationships, particularly involving the pronouns "her" and "my"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AutoField
    -0.49
    tonode
    -0.49
     nele
    -0.44
    astres
    -0.43
    Liza
    -0.43
     yağı
    -0.42
    ffekt
    -0.42
     Aja
    -0.42
    нок
    -0.42
     hazard
    -0.41
    POSITIVE LOGITS
     Their
    1.05
    Their
    1.03
    脚注の使い方
    0.96
     My
    0.86
    ]--;
    0.85
     Our
    0.83
    Datuak
    0.82
    rawDesc
    0.82
    whose
    0.79
    enumii
    0.79
    Act Density 0.194%

    No Known Activations