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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases and expressions indicating superiority or competition

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

    making comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.53
     AssemblyCulture
    -0.52
    SequentialGroup
    -0.52
     resourceCulture
    -0.51
    RenderAtEndOf
    -0.42
    Personendaten
    -0.41
    Handlung
    -0.40
    providedIn
    -0.39
     CanadaChoose
    -0.39
    createClass
    -0.38
    POSITIVE LOGITS
     Compare
    0.70
    Compare
    0.67
     compare
    0.66
     compares
    0.63
     Comparing
    0.63
    Comparing
    0.61
     surpass
    0.61
     superior
    0.60
    Superior
    0.59
     Comparable
    0.59
    Act Density 0.171%

    No Known Activations