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

    Neuronpedia

    INDEX
    Explanations

    the presence of the word "additionally."

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

    consequently, additionally, accordingly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SceneManagement
    -0.44
    存于互联网档案馆
    -0.44
    ​—
    -0.44
    _-
    -0.43
     ơn
    -0.43
    Gua
    -0.41
    UPC
    -0.41
    DOCTYPE
    -0.40
      
    -0.40
    Kow
    -0.40
    POSITIVE LOGITS
    ificantly
    0.72
    denly
    0.69
    tionally
    0.67
     ivelany
    0.67
    ALLY
    0.65
    tically
    0.63
    ätzlich
    0.62
    ically
    0.62
    ATELY
    0.61
    ulously
    0.60
    Act Density 0.020%

    No Known Activations