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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "take" in various contexts

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

    take long

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    terly
    -0.54
    ibatis
    -0.53
    berton
    -0.51
    lossary
    -0.50
    letzt
    -0.50
     IFF
    -0.50
     Border
    -0.49
    llan
    -0.49
    テンツ
    -0.48
    lloworld
    -0.48
    POSITIVE LOGITS
     take
    0.41
    Take
    0.41
     taken
    0.39
     TAKE
    0.38
     desmotivaciones
    0.38
     wzi
    0.38
     Take
    0.38
     tomado
    0.36
     Maier
    0.36
     tomada
    0.36
    Act Density 0.011%

    No Known Activations