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

    Neuronpedia

    INDEX
    Explanations

    closing brackets and parentheses in code structures

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

    Code snippets or alternatives (else, otherwise)

    np_acts-logits-general · gemini-2.0-flash

    else or otherwise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ЖК
    -0.47
    acea
    -0.46
    pegno
    -0.44
    idase
    -0.43
     Wohl
    -0.43
    ighth
    -0.43
    anadium
    -0.43
     Repr
    -0.42
     pula
    -0.42
     pur
    -0.42
    POSITIVE LOGITS
    setVerticalGroup
    0.90
    else
    0.87
     rather
    0.86
    rather
    0.86
     else
    0.85
     ELSE
    0.85
     alternatively
    0.79
     whereas
    0.79
     Altri
    0.78
     otherwise
    0.78
    Act Density 0.164%

    No Known Activations