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

    Neuronpedia

    INDEX
    Explanations

    words related to physical actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ritz
    -0.15
    grown
    -0.15
    обов
    -0.15
    onda
    -0.15
    iders
    -0.14
    大人
    -0.14
    orta
    -0.14
    long
    -0.13
    á»ĵ
    -0.13
    paid
    -0.13
    POSITIVE LOGITS
    lessly
    0.25
    aneously
    0.22
    ishly
    0.20
    ily
    0.19
    ize
    0.19
    astically
    0.18
    istically
    0.18
    uously
    0.18
    ify
    0.18
    itize
    0.17
    Act Density 0.191%

    No Known Activations