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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate ways or forms of actions or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     one
    -0.23
    ุà¸Ķ
    -0.16
     íķĺëĤĺ
    -0.15
     одно
    -0.14
    à¹Ģà¸Ľà¸¥
    -0.14
    äºĪ
    -0.14
    ä¸Ģ次
    -0.14
    oka
    -0.14
    /parser
    -0.14
    WithOptions
    -0.14
    POSITIVE LOGITS
     another
    0.35
     or
    0.32
    another
    0.31
     Another
    0.28
    Another
    0.28
     oder
    0.28
    åı¦
    0.24
     или
    0.24
    æĪĸ
    0.23
     atau
    0.23
    Act Density 0.010%

    No Known Activations