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

    Neuronpedia

    INDEX
    Explanations

    phrases related to subjective observations or assessments

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

    appears, looks, seems + to/that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     feed
    -0.42
    gab
    -0.42
    $_['
    -0.42
     put
    -0.41
    LookAndFeel
    -0.41
     Wass
    -0.41
     have
    -0.40
    леб
    -0.39
    webdriver
    -0.38
     continuant
    -0.38
    POSITIVE LOGITS
    EDEFAULT
    0.83
    تقاوى
    0.79
    IntoConstraints
    0.77
    :✨
    0.77
     EconPapers
    0.76
     tartalomajánló
    0.75
     defaultstate
    0.74
    TypedDataSet
    0.74
    Geplaatst
    0.73
    RTLD
    0.73
    Act Density 0.095%

    No Known Activations