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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating capability or assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    exitRule
    -0.61
    SharedDtor
    -0.60
    belong
    -0.57
     belonging
    -0.54
     Regula
    -0.54
    HomeAsUpEnabled
    -0.53
    Portale
    -0.53
    omitempty
    -0.51
     okuyayım
    -0.51
     препратки
    -0.49
    POSITIVE LOGITS
     fallu
    0.81
     did
    0.76
     potuto
    0.71
     Савезне
    0.67
     пришлось
    0.66
     helped
    0.65
     udało
    0.63
     Мексичка
    0.62
     pudieron
    0.62
    szön
    0.62
    Act Density 0.301%

    No Known Activations