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

    Neuronpedia

    INDEX
    Explanations

    relative quantifiers that express size or amount

    oai_token-act-pair · gemini-2.0-flash

    terms related to quantity or proportion

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

    Proportions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.93
    InjectAttribute
    -0.88
    quite
    -0.87
     quite
    -0.85
     nahilalakip
    -0.84
     very
    -0.83
    OGND
    -0.83
    httphttps
    -0.81
    RenderAtEndOf
    -0.80
    findpost
    -0.78
    POSITIVE LOGITS
     percentage
    0.68
     proportion
    0.60
     portion
    0.52
     Percentage
    0.51
     subset
    0.50
     Percent
    0.49
     percent
    0.47
     chunk
    0.47
     cohort
    0.47
     fraction
    0.47
    Act Density 1.982%

    No Known Activations