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

    Neuronpedia

    INDEX
    Explanations

    sentences that indicate conclusions or results

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

    Therefore

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    listi
    -0.66
    NICK
    -0.65
    ack
    -0.61
     Drill
    -0.61
    nick
    -0.60
    uck
    -0.60
    masking
    -0.60
     Kuli
    -0.60
    Robin
    -0.60
    Duck
    -0.60
    POSITIVE LOGITS
    Therefore
    1.55
     Therefore
    1.52
     therefore
    1.26
    Поэтому
    1.21
     Portanto
    1.20
    therefore
    1.18
     Поэтому
    1.12
     derfor
    1.06
     Derfor
    1.02
     Daarom
    1.02
    Act Density 0.022%

    No Known Activations