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

    Neuronpedia

    INDEX
    Explanations

    text discussing online shopping, coupons, homework help, assignments and starch analysis.

    oai_token-act-pair · gemini-2.0-flash

    uncommon suffixes or non-standard terms

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

    Random internet text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mergeFrom
    -0.80
    tvguidetime
    -0.75
     myſelf
    -0.71
    yntaxException
    -0.69
     Савезне
    -0.69
     Mahomet
    -0.68
    utilisons
    -0.67
     GeoNames
    -0.67
     itſelf
    -0.67
    $")
    -0.65
    POSITIVE LOGITS
     ones
    0.56
     het
    0.50
    な
    0.48
    andet
    0.48
     amount
    0.47
     colspan
    0.47
     pair
    0.47
    ไ
    0.47
     vostri
    0.47
    SessionFactory
    0.46
    Act Density 0.689%

    No Known Activations