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

    Neuronpedia

    INDEX
    Explanations

    references to increasing trends or quantities

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

    growing followed by a noun signifying increase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    qtype
    -0.47
     endblock
    -0.46
     StyleSheet
    -0.45
    ificity
    -0.42
     koszulka
    -0.42
     kurtka
    -0.42
    nalpot
    -0.41
    spreis
    -0.41
     niego
    -0.40
    écnicas
    -0.40
    POSITIVE LOGITS
     growing
    0.60
     emerging
    0.59
    growing
    0.59
     crescente
    0.59
     creciente
    0.57
     Increasing
    0.55
    increasing
    0.55
    expandindo
    0.55
    Increasing
    0.55
     declining
    0.54
    Act Density 0.021%

    No Known Activations