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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "frequently" and its variants, highlighting occurrences or patterns that happen often

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NameInMap
    -0.77
     pus
    -0.66
    ERMIN
    -0.65
    MathML
    -0.64
    underbrace
    -0.63
     ilmiah
    -0.59
     estimés
    -0.58
     تانيه
    -0.58
     Cardona
    -0.58
    osh
    -0.58
    POSITIVE LOGITS
     frequent
    2.15
     frequently
    2.14
    Frequent
    2.00
    frequently
    1.98
     Frequent
    1.98
    frequent
    1.97
     Frequently
    1.91
     fréquemment
    1.72
     frequency
    1.57
     frequ
    1.52
    Act Density 0.097%

    No Known Activations