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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with "In" or "On" that indicate temporal or contextual transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    introducing specific contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     infatti
    -0.57
    SharedCtor
    -0.55
    følgelig
    -0.51
     ainfi
    -0.50
    couvrez
    -0.46
     fometimes
    -0.46
     mijne
    -0.46
     chiunque
    -0.45
     apapun
    -0.45
    出版年
    -0.44
    POSITIVE LOGITS
     Meanwhile
    0.64
    Separ
    0.61
    Meanwhile
    0.61
    Elsewhere
    0.61
     meanwhile
    0.61
    另外
    0.59
     elsewhere
    0.58
     other
    0.57
     lastly
    0.56
     Elsewhere
    0.56
    Act Density 0.054%

    No Known Activations