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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating an increasing trend or frequency

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

    more and increasingly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chwiliwch
    -0.59
    UrlResolution
    -0.59
    UnusedPrivate
    -0.57
    abestanden
    -0.52
     ब्रेकडाउन
    -0.51
     onResponse
    -0.50
     nahilalakip
    -0.49
     disponibilités
    -0.49
     ProtoMessage
    -0.47
     للمعارف
    -0.45
    POSITIVE LOGITS
    addCriterion
    0.43
    asius
    0.39
     semakin
    0.38
    ってきて
    0.38
     bit
    0.38
     watchful
    0.38
    ))^
    0.38
     increasingly
    0.37
    acebook
    0.37
    AxisAlignment
    0.37
    Act Density 0.012%

    No Known Activations