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

    Neuronpedia

    INDEX
    Explanations

    references to singular and plural forms of the word "one" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    land
    -0.20
     one
    -0.18
    thane
    -0.17
    cape
    -0.17
    ron
    -0.16
    walker
    -0.16
    ä¸Ģä¸ĭ
    -0.16
    ÚĨÙĩ
    -0.16
    Ùĩا
    -0.16
    th
    -0.16
    POSITIVE LOGITS
    -sided
    0.27
    -third
    0.26
    ida
    0.26
    -eyed
    0.26
    -dimensional
    0.26
    -handed
    0.23
    onta
    0.23
    idas
    0.23
    -bedroom
    0.22
    -way
    0.21
    Act Density 0.067%

    No Known Activations