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

    Neuronpedia

    INDEX
    Explanations

    the repetition of the word "same" in various contexts

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

    same following a descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reconna
    -0.35
     réc
    -0.35
    LEIA
    -0.35
     crí
    -0.34
     fug
    -0.33
    ikation
    -0.33
     []:
    -0.32
     constr
    -0.32
    AutoScaleMode
    -0.32
    Vikt
    -0.32
    POSITIVE LOGITS
    同じく
    0.71
    ⤹
    0.59
     Likewise
    0.59
    zelfde
    0.56
    同様に
    0.54
    Likewise
    0.54
     esternos
    0.52
    锈钢
    0.49
    ⟬
    0.49
     Similarly
    0.49
    Act Density 0.005%

    No Known Activations