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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate comparisons or contrasts between subjects

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

    "compared with" or similar comparison phrases

    np_acts-logits-general · gemini-2.0-flash

    comparing items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    первых
    -0.60
     BoxDecoration
    -0.60
    gdx
    -0.59
    یتی
    -0.57
    colgroup
    -0.57
    pedes
    -0.56
     HasFactory
    -0.55
    pyx
    -0.54
    hilfe
    -0.54
     Audiodateien
    -0.54
    POSITIVE LOGITS
     compares
    0.89
    compar
    0.87
     Comparing
    0.86
     comparisons
    0.86
     Comparisons
    0.85
     COMPAR
    0.82
     comparing
    0.81
    Comparing
    0.80
     comparer
    0.80
     comparison
    0.80
    Act Density 0.136%

    No Known Activations