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

    Neuronpedia

    INDEX
    Explanations

    phrases related to power dynamics and control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.71
    principalColumn
    -0.57
    SharedCtor
    -0.54
    Nazionale
    -0.54
     stater
    -0.54
     vesta
    -0.52
    StructEnd
    -0.52
     isInitialized
    -0.51
    }`}
    -0.51
     تانيه
    -0.51
    POSITIVE LOGITS
     countless
    0.71
     densely
    0.62
    Numerous
    0.62
     endless
    0.61
     Numerous
    0.61
     innumerable
    0.60
     boundless
    0.60
     scenes
    0.58
    companied
    0.57
     scene
    0.57
    Act Density 0.055%

    No Known Activations