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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases emphasizing purpose or intent

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

    <start_of_turn> user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </thead>
    -0.37
     sending
    -0.36
     Driver
    -0.36
    Driver
    -0.35
    Adres
    -0.34
     Zus
    -0.34
     editors
    -0.33
     konk
    -0.33
     pushing
    -0.33
     instinctively
    -0.33
    POSITIVE LOGITS
    parsedMessage
    0.57
    ftagPool
    0.55
    uestamente
    0.53
     Италијани
    0.52
    :✨
    0.52
     snippetHide
    0.52
    MessageOf
    0.52
    createCanvas
    0.51
     noDo
    0.50
    SerializedSize
    0.49
    Act Density 0.000%

    No Known Activations