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

    Neuronpedia

    INDEX
    Explanations

    references to societal roles and identities, particularly in the context of community involvement and responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adors
    -0.21
    adores
    -0.21
     bart
    -0.17
    wives
    -0.16
    encers
    -0.16
    imps
    -0.16
     chicas
    -0.16
    adoras
    -0.16
    enders
    -0.16
    chers
    -0.16
    POSITIVE LOGITS
     person
    0.42
     member
    0.39
     employee
    0.34
     participant
    0.33
     inhabit
    0.32
     worker
    0.32
     player
    0.31
     guy
    0.31
    member
    0.29
    person
    0.26
    Act Density 1.691%

    No Known Activations