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

    Neuronpedia

    INDEX
    Explanations

    underscores followed by commas in a structured data format

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    argout
    -0.75
     Fod
    -0.70
     Audiodateien
    -0.63
    mored
    -0.62
     /\.
    -0.61
    ждествен
    -0.60
    WebServlet
    -0.58
     Dand
    -0.58
     fini
    -0.57
    ErrUnexpectedEOF
    -0.57
    POSITIVE LOGITS
     للمعارف
    0.77
     resourceCulture
    0.60
     _,
    0.58
    featureID
    0.56
     فريبيس
    0.55
    Bioaccumulative
    0.54
    stärke
    0.50
    lihatan
    0.50
    gameserver
    0.50
     Olímp
    0.49
    Act Density 0.001%

    No Known Activations