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

    Neuronpedia

    INDEX
    Explanations

    words related to strength and strong characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    exitRule
    -0.54
    CPtr
    -0.51
     [](
    -0.50
     abzu
    -0.48
    JsonPropertyName
    -0.47
     Ota
    -0.47
     setTime
    -0.46
    [](
    -0.45
    Tembelea
    -0.45
     abz
    -0.45
    POSITIVE LOGITS
    strong
    1.23
     strong
    1.21
     Strong
    1.19
    STRONG
    1.18
    Strong
    1.17
     STRONG
    1.15
    Strength
    1.09
     strongest
    1.06
     stronger
    1.06
     strength
    1.06
    Act Density 0.135%

    No Known Activations