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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate duality or inclusion of multiple elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irc
    -0.15
    adan
    -0.14
    à¤ķन
    -0.14
    ženÃŃ
    -0.14
    _usec
    -0.13
    undry
    -0.13
    strt
    -0.13
    ili
    -0.13
    åIJįçĦ¡ãģĹãģķãĤĵ
    -0.12
    à¥ģà¤ļ
    -0.12
    POSITIVE LOGITS
     animate
    0.22
     indoors
    0.21
     static
    0.20
     numerator
    0.19
     overt
    0.18
     weekdays
    0.17
     male
    0.17
     sexes
    0.17
     single
    0.17
    either
    0.17
    Act Density 0.552%

    No Known Activations