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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "stay" and variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ChromeDriver
    -0.59
    LEncoder
    -0.54
    Duncan
    -0.52
    epresidente
    -0.51
    ceps
    -0.51
    InjectMocks
    -0.50
    Emails
    -0.50
     Newton
    -0.49
     publicitaires
    -0.49
     TableColumn
    -0.49
    POSITIVE LOGITS
     Stay
    0.71
    Stay
    0.69
     sojourn
    0.66
    stay
    0.66
     Aufenthalt
    0.59
     stay
    0.59
     estadia
    0.58
     пребы
    0.57
    STAY
    0.55
     Aufenthal
    0.54
    Act Density 0.003%

    No Known Activations