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

    Neuronpedia

    INDEX
    Explanations

    phrases related to awareness and understanding of social issues

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

    awareness of knowledge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.73
     disambiguazione
    -0.71
    Personensuche
    -0.68
    OrNil
    -0.59
    twimg
    -0.57
    MigrationBuilder
    -0.57
     GenerationType
    -0.56
     fhort
    -0.56
    lorette
    -0.55
    addCriterion
    -0.55
    POSITIVE LOGITS
     EXPOSURE
    0.39
     exposure
    0.35
    exposure
    0.34
    知识
    0.33
     Exposure
    0.31
    InteropServices
    0.31
     transparency
    0.31
     knowledge
    0.30
     conocimiento
    0.30
    Exposure
    0.30
    Act Density 0.083%

    No Known Activations