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

    Neuronpedia

    INDEX
    Explanations

    key themes related to power dynamics and control within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ANTE
    -0.16
    ante
    -0.16
    RTC
    -0.15
    átek
    -0.14
    tings
    -0.14
     Imports
    -0.14
    ãģ¼
    -0.14
     Vintage
    -0.14
    103
    -0.13
    agento
    -0.13
    POSITIVE LOGITS
    erra
    0.15
    avier
    0.14
    oland
    0.14
    ode
    0.14
    ergy
    0.14
    egra
    0.13
    umba
    0.13
    .scalablytyped
    0.13
    oden
    0.13
    Ŀå§ĭ
    0.13
    Act Density 0.259%

    No Known Activations