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

    Neuronpedia

    INDEX
    Explanations

    instances of conjunctions and phrases indicating inclusion or and/or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     åıĪ
    -0.15
     либо
    -0.14
    bir
    -0.14
    زÙħاÙĨ
    -0.14
     EITHER
    -0.14
    åıĪ
    -0.14
    anza
    -0.13
    atas
    -0.13
    hari
    -0.13
     //~
    -0.12
    POSITIVE LOGITS
     etc
    0.40
     others
    0.39
    etc
    0.36
     other
    0.35
     many
    0.35
    others
    0.28
    Others
    0.27
    ãģĿãģ®ä»ĸ
    0.27
     numerous
    0.26
    many
    0.26
    Act Density 0.163%

    No Known Activations