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

    Neuronpedia

    INDEX
    Explanations

    instances of exaggeration or hyperbole in descriptions

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

    exaggeration and hyperbole

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     חיצוניים
    -0.40
     us
    -0.37
    帖最后由
    -0.35
     chips
    -0.35
     Ari
    -0.35
     Tobin
    -0.34
     Gauthier
    -0.34
    SqlClient
    -0.34
     Clu
    -0.33
    站
    -0.33
    POSITIVE LOGITS
     exaggerate
    1.13
     exaggerating
    1.09
     exaggerated
    1.08
     exaggeration
    1.00
     exagger
    0.93
     exager
    0.91
    夸张
    0.88
     exag
    0.79
    ValueStyle
    0.77
     magnified
    0.62
    Act Density 0.019%

    No Known Activations