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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "thin" and its variations, indicating a focus on thinness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eb
    -0.17
    ãĥ¼ãĥ
    -0.16
    ains
    -0.16
    ufen
    -0.16
    ein
    -0.15
    inous
    -0.15
    vil
    -0.15
    iences
    -0.15
    ean
    -0.14
    hem
    -0.14
    POSITIVE LOGITS
    ning
    0.39
    NING
    0.26
    ners
    0.23
    ening
    0.23
    /th
    0.22
     slice
    0.21
     slices
    0.20
    ness
    0.20
     gauge
    0.20
    kest
    0.19
    Act Density 0.025%

    No Known Activations