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

    Neuronpedia

    INDEX
    Explanations

    references to family and household relationships

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

    family and household members

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    XMLSchema
    -0.38
     trial
    -0.38
     fucked
    -0.38
     negli
    -0.35
     Bog
    -0.35
     closure
    -0.35
    Références
    -0.35
     set
    -0.34
     contradicted
    -0.34
     mess
    -0.33
    POSITIVE LOGITS
    family
    0.64
    Family
    0.56
     FAMILY
    0.55
    FAMILY
    0.55
     family
    0.55
    thâu
    0.54
     famille
    0.54
    👪
    0.54
    AddTagHelper
    0.52
    usermodel
    0.52
    Act Density 0.010%

    No Known Activations