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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "thin" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥ
    -0.17
    iences
    -0.17
    eb
    -0.16
    inous
    -0.15
    ufen
    -0.15
    ean
    -0.15
    hem
    -0.15
    ein
    -0.15
    pheres
    -0.14
    ains
    -0.14
    POSITIVE LOGITS
    ning
    0.43
    NING
    0.28
    ners
    0.26
    ening
    0.25
    ness
    0.24
    kest
    0.22
    /th
    0.21
    ningen
    0.20
    ened
    0.20
     slice
    0.20
    Act Density 0.023%

    No Known Activations