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

    Neuronpedia

    INDEX
    Explanations

    references to fat in various contexts

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

    the word "fat"

    np_acts-logits-general · gemini-2.0-flash

    fat variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Italijani
    -0.77
     tartalomajánló
    -0.76
     gynhyrchwyd
    -0.74
     □
    -0.73
     disambiguazione
    -0.73
    withIdentifier
    -0.73
    -0.72
    Билгалдахарш
    -0.72
     chamomile
    -0.72
    wpi
    -0.72
    POSITIVE LOGITS
     fat
    1.05
     Fat
    0.91
    fat
    0.90
    Fat
    0.86
    FAT
    0.81
     Fats
    0.78
     FAT
    0.74
     fats
    0.73
     fatt
    0.73
     fatty
    0.68
    Act Density 0.145%

    No Known Activations