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

    Neuronpedia

    INDEX
    Explanations

    phrases related to user input and email entry forms

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

    entering data prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     referrerpolicy
    -0.62
    GEBURTSDATUM
    -0.58
    sizeCache
    -0.57
    parsedMessage
    -0.56
     GenerationType
    -0.54
    styleType
    -0.54
    featureID
    -0.53
     ObjectParameter
    -0.52
    SOUNDBITE
    -0.52
    Personendaten
    -0.51
    POSITIVE LOGITS
     entered
    0.90
     enters
    0.89
     enter
    0.85
     Entering
    0.85
     Enter
    0.85
    entered
    0.81
     entering
    0.79
    Enter
    0.79
     Entry
    0.77
     Entered
    0.77
    Act Density 0.040%

    No Known Activations