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

    Neuronpedia

    INDEX
    Explanations

    descriptors associated with toxic or narcissistic behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .gb
    -0.16
    xAA
    -0.15
    ên
    -0.14
    ollen
    -0.14
    éĩ
    -0.14
    ·¸
    -0.14
    oub
    -0.14
     Pregnancy
    -0.14
    .logic
    -0.14
    éľĬ
    -0.13
    POSITIVE LOGITS
     Narc
    0.33
     narciss
    0.30
     personality
    0.26
     Border
    0.24
     Cluster
    0.24
     Personality
    0.24
     soci
    0.23
     traits
    0.22
     borderline
    0.22
    Border
    0.21
    Act Density 0.024%

    No Known Activations