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

    Neuronpedia

    INDEX
    Explanations

    specific words associated with commands or actions related to accounts and buttons in a user interface context

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

    words beginning with Con

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    d
    -0.40
     d
    -0.39
    uro
    -0.38
    yn
    -0.38
    end
    -0.38
    bul
    -0.38
    m
    -0.38
    ble
    -0.37
    ec
    -0.36
     
    -0.36
    POSITIVE LOGITS
     themſelves
    0.61
     transfieras
    0.61
    GEBURTSDATUM
    0.60
     pinulongan
    0.60
    хьтан
    0.60
     myſelf
    0.60
     whoſe
    0.59
    Σε
    0.57
     leaſt
    0.57
    Rüyada
    0.57
    Act Density 0.041%

    No Known Activations