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

    Neuronpedia

    INDEX
    Explanations

    numerical data and statistics

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

    numbers followed by commas or other numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     therefore
    -0.32
     Außerdem
    -0.31
     además
    -0.29
     infatti
    -0.29
     donc
    -0.28
    W
    -0.28
    I
    -0.27
    Therefore
    -0.26
    B
    -0.26
     Therefore
    -0.26
    POSITIVE LOGITS
    <unused68>
    1.09
    <unused41>
    1.09
    [@BOS@]
    1.09
    <unused3>
    1.09
    <unused43>
    1.09
    <unused51>
    1.09
    <unused23>
    1.09
    <unused17>
    1.09
    <unused8>
    1.09
    <unused14>
    1.09
    Act Density 0.269%

    No Known Activations