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

    Neuronpedia

    INDEX
    Explanations

    elements relating to interpersonal dynamics and relationship challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PARATUS
    -0.58
    铵
    -0.54
     Lobby
    -0.52
     müh
    -0.52
    DaoImpl
    -0.51
    Hozzáférés
    -0.51
    GIVEREF
    -0.50
    myra
    -0.50
    AsStream
    -0.50
    ciorys
    -0.49
    POSITIVE LOGITS
     toxic
    0.75
     Narcis
    0.74
     hurtful
    0.74
     narcis
    0.73
     toxicity
    0.72
     manipulative
    0.71
     boundaries
    0.70
     hurt
    0.70
     narcissist
    0.70
     relationship
    0.69
    Act Density 0.462%

    No Known Activations