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

    Neuronpedia

    INDEX
    Explanations

    words related to value and performance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adera
    -0.16
    836
    -0.15
    846
    -0.15
    ism
    -0.15
     Christianity
    -0.14
    erty
    -0.14
    tery
    -0.14
    onya
    -0.14
     purpose
    -0.14
     Specialty
    -0.13
    POSITIVE LOGITS
     economic
    0.24
     political
    0.24
     financial
    0.23
     compos
    0.22
     culinary
    0.21
    political
    0.21
     artistic
    0.21
     academic
    0.21
     administrative
    0.21
     journalistic
    0.20
    Act Density 0.109%

    No Known Activations