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

    Neuronpedia

    INDEX
    Explanations

    references to interpersonal boundaries and conflicts in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iffies
    -0.18
    éf
    -0.17
    unga
    -0.16
    éĽħ
    -0.16
    ucci
    -0.16
    'field
    -0.14
    жди
    -0.14
    èĮĤ
    -0.14
    âĺĨ
    -0.14
    .swt
    -0.14
    POSITIVE LOGITS
     demanding
    0.19
     interfering
    0.18
     nag
    0.18
     intrusive
    0.18
     unwanted
    0.17
     annoying
    0.17
     push
    0.17
     insistence
    0.16
     pest
    0.16
     entitled
    0.16
    Act Density 0.255%

    No Known Activations