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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and expressions of uncertainty

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

    after "is" or forms of "to be"

    np_acts-logits-general · gemini-2.0-flash

    learned aboutbecome moretoo conservativesimple fact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    -0.35
     statt
    -0.34
    down
    -0.31
    1
    -0.30
    N
    -0.30
    "
    -0.30
    “
    -0.29
    |
    -0.29
    IN
    -0.28
    s
    -0.28
    POSITIVE LOGITS
    <unused41>
    1.03
    [@BOS@]
    1.03
    <unused3>
    1.02
    <unused8>
    1.02
    <unused43>
    1.02
    <unused51>
    1.02
    <unused42>
    1.02
    <unused28>
    1.02
    <unused14>
    1.02
    <unused16>
    1.02
    Act Density 0.750%

    No Known Activations