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

    Neuronpedia

    INDEX
    Explanations

    references to strength or strong attributes in various contexts

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

    strong adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تعدى
    -0.36
     experiments
    -0.31
     wonder
    -0.29
     actionTypes
    -0.29
     access
    -0.29
     Aufenthalt
    -0.29
     apprend
    -0.29
     visits
    -0.29
     methods
    -0.28
     wonders
    -0.28
    POSITIVE LOGITS
     strong
    1.10
    strong
    0.98
    STRONG
    0.94
    Strong
    0.91
     STRONG
    0.89
     Strong
    0.88
     sterke
    0.87
     propOrder
    0.87
     strongly
    0.83
     strongest
    0.82
    Act Density 0.016%

    No Known Activations