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

    Neuronpedia

    INDEX
    Explanations

    references to interpersonal relationships and the concept of "us" versus "them."

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

    Follows personal pronouns, numbers, or professions

    np_acts-logits-general · gemini-2.0-flash

    references to people and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.79
     Савезне
    -0.68
     nakalista
    -0.67
    RegressionTest
    -0.63
    IndentedString
    -0.63
    帖最后由
    -0.62
    IsContent
    -0.61
    Vidite
    -0.60
    matchCondition
    -0.60
    AutoField
    -0.60
    POSITIVE LOGITS
     minu
    0.32
     concentración
    0.30
     lymphoma
    0.30
     hembra
    0.29
    avadoc
    0.29
     discriminación
    0.28
    ass
    0.28
    工作人员
    0.28
     demo
    0.28
     freiw
    0.28
    Act Density 0.576%

    No Known Activations