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

    Neuronpedia

    INDEX
    Explanations

    varied topics related to science, politics, and finance, sometimes with positive or negative connotations.

    oai_token-act-pair · gemini-2.0-flash

    roles related to creators and makers

    np_token-act-pair-logits · gpt-4o-mini

    ending "er"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     défendre
    -0.65
     préciser
    -0.63
     détruire
    -0.61
     remarquer
    -0.60
     couvrir
    -0.59
     refusé
    -0.59
     mourir
    -0.59
     prouver
    -0.57
     satisfaire
    -0.57
     بيها
    -0.56
    POSITIVE LOGITS
     maker
    0.94
     creator
    0.94
     searcher
    0.93
     builder
    0.92
     tester
    0.90
    izer
    0.88
     provider
    0.86
     giver
    0.85
     creators
    0.85
     scorer
    0.84
    Act Density 11.492%

    No Known Activations