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

    Neuronpedia

    INDEX
    Explanations

    references to saddles and related terms

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

    saddle and rider concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ria
    -0.50
     Ria
    -0.48
     Blitz
    -0.48
     millionaire
    -0.47
     Greene
    -0.47
     referenties
    -0.47
    省市镇
    -0.46
    炎
    -0.46
    fiq
    -0.46
     Vicky
    -0.46
    POSITIVE LOGITS
     saddle
    2.22
     Saddle
    1.98
     saddles
    1.78
     Sadd
    1.37
    addle
    1.29
     sadd
    1.21
    鞍
    0.91
     Sadler
    0.65
     rider
    0.64
     caballos
    0.62
    Act Density 0.004%

    No Known Activations