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

    Neuronpedia

    INDEX
    Explanations

    instances of the phrase "return to" in various contexts

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

    return to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    complexContent
    -0.56
    arangay
    -0.54
     ſche
    -0.52
    stdc
    -0.52
    aguay
    -0.52
     ſch
    -0.52
    orance
    -0.51
    -0.51
     compiler
    -0.50
     whatnot
    -0.50
    POSITIVE LOGITS
     referenties
    0.51
     tornare
    0.49
     verlassen
    0.49
     meninggalkan
    0.47
     Rückkehr
    0.47
     rejoin
    0.47
    回到
    0.46
     abbandon
    0.45
     wró
    0.44
     lasciare
    0.44
    Act Density 0.012%

    No Known Activations