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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "strong" and related terms indicating strength or power

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

    Comes after "strong"

    np_acts-logits-general · gemini-2.0-flash

    strong followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    exitRule
    -0.56
    CPtr
    -0.54
    JsonPropertyName
    -0.46
     [](
    -0.45
     setTime
    -0.45
     abzu
    -0.44
    [:-
    -0.44
     abz
    -0.44
    [](
    -0.43
    Tembelea
    -0.43
    POSITIVE LOGITS
    strong
    1.31
     strong
    1.25
    Strong
    1.21
     Strong
    1.21
    STRONG
    1.20
     STRONG
    1.17
     strongest
    1.05
     stronger
    1.02
    Strength
    1.00
    strength
    0.98
    Act Density 0.086%

    No Known Activations