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

    Neuronpedia

    INDEX
    Explanations

    the word "Nonetheless" in various forms, indicating a transition or contrast in statements

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

    introducing contrast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ☛
    -0.51
    ViewById
    -0.47
     gouver
    -0.46
    XCTAssert
    -0.46
     hadas
    -0.45
     kark
    -0.45
    rý
    -0.45
     recargable
    -0.45
    ☞
    -0.44
    nativeElement
    -0.44
    POSITIVE LOGITS
    Nonetheless
    1.38
     Nonetheless
    1.34
     nonetheless
    1.29
    etheless
    1.13
    retudo
    0.62
     '\\;'
    0.60
    nene
    0.57
    indest
    0.55
     tokenize
    0.54
    moke
    0.53
    Act Density 0.017%

    No Known Activations