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

    Neuronpedia

    INDEX
    Explanations

    the concept or idea referenced in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ásban
    -0.62
    iduous
    -0.60
     hår
    -0.60
    on
    -0.59
     resistenza
    -0.58
    abon
    -0.57
     rou
    -0.56
    ri
    -0.56
     strconv
    -0.55
    SafeArea
    -0.54
    POSITIVE LOGITS
     concepts
    1.72
     concept
    1.56
     CONCEPT
    1.49
     Concepts
    1.46
    Concepts
    1.44
     Concept
    1.40
    Concept
    1.35
    concepts
    1.32
    concept
    1.31
     CONCEPTS
    1.24
    Act Density 0.052%

    No Known Activations