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

    Neuronpedia

    INDEX
    Explanations

    phrases that discuss dualities or contrasting options in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ειτουργ
    -0.63
     leksikon
    -0.61
    setof
    -0.60
     almeno
    -0.60
    ########.
    -0.59
     Wikimedijinoj
    -0.59
     хотя
    -0.58
     Wikidata
    -0.57
     kasarigan
    -0.56
     referenties
    -0.56
    POSITIVE LOGITS
     either
    1.16
    either
    1.00
     Either
    0.89
     whether
    0.89
    Either
    0.83
     entweder
    0.76
    owohl
    0.74
     Whether
    0.73
    whether
    0.73
     male
    0.72
    Act Density 0.714%

    No Known Activations