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

    Neuronpedia

    INDEX
    Explanations

    references to body weight, specifically relating to fat and related descriptors

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

    fat or fatness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.63
    новниш
    -0.62
     <>",
    -0.58
    parsedMessage
    -0.55
    fjspx
    -0.53
     يتيمه
    -0.52
    AddTagHelper
    -0.51
    tagHelperRunner
    -0.50
    AnimationsModule
    -0.49
    writeFieldEnd
    -0.49
    POSITIVE LOGITS
    fat
    0.73
     Fat
    0.73
    Fat
    0.72
     fat
    0.70
     FAT
    0.65
    FAT
    0.63
    Fatty
    0.55
    tened
    0.54
     Fats
    0.54
     Fatty
    0.54
    Act Density 0.019%

    No Known Activations