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

    Neuronpedia

    INDEX
    Explanations

    phrases related to perceived observation, particularly in contexts of surveillance and bodily sensations or symptoms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    elements related to surveillance and physical privacy concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    physical, tangible, visible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rospy
    -0.57
     inflater
    -0.54
    KURZBESCHREIBUNG
    -0.50
    harusnya
    -0.49
    aktery
    -0.48
     ética
    -0.48
     înc
    -0.47
    Liet
    -0.46
    .*")]
    -0.46
     Blacklist
    -0.46
    POSITIVE LOGITS
     tangible
    1.82
     physical
    1.82
    physical
    1.57
     Physical
    1.55
    Physical
    1.53
     visible
    1.51
     physically
    1.49
     PHYSICAL
    1.47
     visual
    1.45
    PHYSICAL
    1.36
    Act Density 0.224%

    No Known Activations