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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating time intervals or durations in the context of studies or observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    таратура
    -0.58
    vaadin
    -0.52
    RoutingModule
    -0.50
    yordu
    -0.47
     intptr
    -0.46
     kasarigan
    -0.46
     eventdata
    -0.45
    HttpFoundation
    -0.45
    存于互联网档案馆
    -0.44
     perfect
    -0.44
    POSITIVE LOGITS
     across
    0.87
     over
    0.85
    across
    0.84
    Across
    0.84
     Across
    0.83
     span
    0.83
     throughout
    0.82
    throughout
    0.80
     spans
    0.79
     ACROSS
    0.79
    Act Density 0.172%

    No Known Activations