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

    Neuronpedia

    INDEX
    Explanations

    instances of co-authorship and collaborative writing in publications

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

    authored articles and experiments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nonUne
    -0.61
     utafitiHapana
    -0.59
     kasarigan
    -0.58
    contentLoaded
    -0.57
    دانشنامهٔ
    -0.56
    出版年
    -0.56
     '\\;'
    -0.55
     externi
    -0.55
     invokingState
    -0.55
    ItemBackground
    -0.53
    POSITIVE LOGITS
    authored
    1.20
     authored
    0.94
    written
    0.67
     authorship
    0.59
     collaboratively
    0.57
    collabor
    0.55
    crafted
    0.55
     collaborative
    0.51
     collaboration
    0.51
     written
    0.51
    Act Density 0.009%

    No Known Activations