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

    Neuronpedia

    INDEX
    Explanations

    concepts related to social class and status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    boys
    -0.21
    adores
    -0.19
    adoras
    -0.17
    stalk
    -0.16
    innen
    -0.16
    ãĥ¼ãĤ¿
    -0.16
    ughters
    -0.16
    embros
    -0.15
    wives
    -0.15
    sons
    -0.15
    POSITIVE LOGITS
     person
    0.65
    person
    0.42
     Person
    0.40
     guy
    0.38
    Person
    0.35
     woman
    0.34
     member
    0.34
     personne
    0.33
     player
    0.33
    _person
    0.32
    Act Density 2.020%

    No Known Activations