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

    Neuronpedia

    INDEX
    Explanations

    references to the second person pronouns "you" and "your."

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

    your possessions, health, actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵↵
    -0.42
    ↵
    -0.39
     
    -0.37
    <eos>
    -0.36
     the
    -0.36
     of
    -0.36
     No
    -0.35
    .
    -0.34
     res
    -0.34
     for
    -0.34
    POSITIVE LOGITS
     AssemblyCulture
    0.94
     queſta
    0.91
    :✨
    0.91
     ſind
    0.87
    <unused16>
    0.87
    <unused8>
    0.87
    <unused14>
    0.86
    <unused17>
    0.86
    <unused3>
    0.86
    [@BOS@]
    0.86
    Act Density 0.045%

    No Known Activations